Staff ML Engineer / Scientist · LLM & Recommendation Systems

Sugeerth Murugesan

I build and evaluate LLM recommendation and agentic systems that survive production.

Retrieval, ranking, and the agentic layers that act on them — productionized and A/B-tested, not just prototyped. Plus the post-training and evaluation behind them.

Book a 20-min intro call Start here → See the featured work ↓ LinkedIn GitHub
5M+Users in production
20+Open-source projects
8Peer-reviewed papers
PhDCS · UC Davis

Every project below links to running code.

Hiring for LLM / RecSys / agentic-AI roles? Start with the three featured builds, skim the recent writing, or just email me — I reply within a day.

LLM Post-Training

  • DPO
  • GRPO
  • RLHF
  • LoRA / QLoRA
  • Distillation

Recommendations

  • Two-tower retrieval
  • Ranking
  • ANN search
  • A/B testing

Agentic Systems

  • LangGraph
  • Multi-agent
  • Tool use
  • Observability

Evaluation

  • LLM-as-Judge
  • RAG eval
  • Reward hacking
  • Eval harnesses

Serving & Infra

  • vLLM
  • SGLang
  • DeepSpeed
  • FSDP / DDP
  • CUDA

About Sugeerth Murugesan

About
Portrait of Sugeerth Murugesan

Sugeerth Murugesan

Staff ML Engineer / Scientist · LLM & Recommendation Systems

I build, train, and evaluate LLM and recommendation systems — post-training, agentic pipelines, retrieval, and the infrastructure behind them.

  • PhD, Computer Science — UC Davis
  • Staff ML Engineer / Scientist — Intel / Intuit
  • Best Paper, ACM-BCB ’16 · US patent, Adobe Research
  • 20+ open-source AI projects — each runnable, with results
Currently

Production systems & open experiments

  • Shipping LLM recommendation + agentic systems in production
  • Open experiments in post-training, RAG, and evaluation
  • Measuring what moves quality and cost — and publishing it
Recommendations LLMs Agentic AI Evaluation
Connect & Explore
sugeerth@gmail.com GitHub LinkedIn Google Scholar Medium Twitter / X More projects →
Research & Industry
Intuit Intel Samba TV Adobe Research UC Davis UC Berkeley Lawrence Berkeley National Lab
02

AI Systems Projects

Production-shaped LLM systems — retrieval, routing, agents, observability, and inference.

RAG Production RAG
Production-grade RAG over private documents: hybrid BM25 + dense retrieval fused via Reciprocal Rank Fusion, cross-encoder reranking, and answers with inline citations traceable to source chunks. Ships prompt-injection detection, confidence-based abstention, and a built-in evaluation suite + monitoring dashboard. FastAPI · ChromaDB · Sentence-Transformers.
Code Overview
Routing LLM Router
Intelligent model routing that scores every model across task match, complexity fit, cost, speed, and context to pick the optimal LLM per query — with Balanced / Max-Quality / Max-Speed / Min-Cost modes across OpenAI and Anthropic models. Runs entirely in the browser, no backend.
Live Code
Agent Observability OMNISCOPE
A multi-agent observability platform that captures the causal DAG of every inter-agent decision (not flat logs), scores quality with a 6-judge LLM panel, predicts failures on the live execution graph, and supports time-travel debugging. Drop-in adapters for LangChain, CrewAI, AutoGen, OpenAI Agents, and Anthropic; judges and embeddings run locally on Ollama.
Live Code
Inference Perf Explorer
An LLM-inference performance explorer: upload model perf sweeps and get a customer go / no-go answer, an engineer sanity-check, and side-by-side comparison — parsed and rendered live in the browser, no backend. React + TypeScript.
Live Code
Multi-Agent Agentic Post-Training Framework
A modular framework where specialized agents coordinate an LLM post-training pipeline — technique selection → training → optimization → evaluation — communicating over a structured message bus so the whole alignment process is observable and debuggable. Apache-2.0, with a Colab + Pages demo.
Live Code
Inference SGLang vs vLLM Playground
A side-by-side LLM-serving benchmark: send the same prompt to SGLang and vLLM, compare outputs, and measure time-to-first-token, total latency, and throughput (tokens/sec) with batch benchmarks and interactive charts. FastAPI backend.
Code
Multi-Agent VoyageAI — Multi-Agent Planner
A supervisor-worker multi-agent system built on LangGraph, LangChain, and Langfuse, where specialized agents (flights, hotels, activities, weather, budget, itinerary) collaborate to produce a plan — with full tracing/observability of the agent graph.
Live Code
03

Research & Experiments

Hypothesis → experiment → measurement. Each project asks a concrete question and reports what the data actually says.

Eval Suite ARES — Agentic RAG Evaluation Suite
F1 0.378 · +28.7% 55 configs swept
Searches the design space of a retrieval-augmented agent — retrieval depth, BM25 / dense hybrid weighting, prompt style, query decomposition, self-reflection — scoring each config on multi-hop QA (HotpotQA) and reporting the quality-vs-cost Pareto frontier. Across 55 configurations, the winner reached F1 0.378 (+28.7% over baseline) at 0.12 s/question. Headline finding: chain-of-thought prompting drove the entire gain — retrieval tuning barely moved F1, and retrieval recall and answer-F1 were decoupled. Runs fully local on Apple Silicon (MPS).
Code Findings
Alignment DPO from Scratch
Direct Preference Optimization on Qwen2.5-0.5B + Anthropic HH-RLHF (8k preference pairs), β=0.1, LoRA — ~35 min on a free T4 — built to show what the chosen / rejected log-probs actually do during training and what β trades off. Includes a write-up: “I ran DPO. Here's what I saw.”
Live Code
SWE-Bench LocalSWEAgent
6/7 patches $0 API cost
A lightweight SWE-bench agent asking whether a 3B model on a laptop can fix real GitHub issues. Honest result: a Qwen2.5-3B agent produced valid patches for 6/7 reachable issues at $0 API cost — but resolved 0%, consistently targeting the wrong root cause. Establishes a zero-cost baseline and pinpoints exactly where small models break down.
Code
GNNs Graph Neural Networks
GAT 81.8% NMI 4.5×
Trains GCN, GAT, and GraphSAGE on the Cora citation network and shows that GNN-learned embeddings capture community structure 4.5× better than raw features (cluster NMI 0.13 → 0.59); GAT reaches 81.8% test accuracy. Interactive attention visualizations + Colab.
Live Code
Training Orchestration Multimodal Training Sweep
A parallel multimodal-LLM training-sweep orchestrator with watchdog crash / stall recovery (halves the batch size and relaunches), SQLite-backed run + metric tracking, an auto-generated comparison dashboard, and a Claude-written verdict on the best variant — auto-published to GitHub Pages.
Live Code
Distributed Training Multi-GPU Training Viz
Trains the same nanoGPT four ways — single-GPU, DDP, FSDP, and DeepSpeed ZeRO-2 — streaming per-step loss, throughput, memory, and grad-norm to JSONL for side-by-side comparison, with a decision tree and documented multi-GPU gotchas. Reproducible on free Colab / Kaggle T4s.
Code
More experiments & live training dashboards on GitHub →
04

More Projects

Earlier interactive builds and data-visualization work — plus the full portfolio archive.

Interactive Viz · Live demo LinkedIn Network Exploration
▶ animated reel Synthetic / fake data D3.js force graph
An interactive D3.js force-directed map of a professional network (~499 people, 2,312 ties) with community detection, location clustering, and betweenness-centrality highlighting, plus an unsupervised “surprise” engine for bridge connections. All data shown is synthetic / fake — no real LinkedIn connections are used.
Live
Portfolio & Project Archive Full archive
The full archive of earlier projects, demos, and visualization work — research software, D3 / web experiments, and side builds collected in one place.
05

Open Source

Tools others can install and run — plus earlier research software licensed by UC / LBNL.

agent-trace-viz Developer Tool · v0.7.0
A pip-installable, drop-in observability tracer for AI agents: one import records the full run as a tree of spans — plans, decisions, tool calls, sub-agent invocations, memory ops, retries, and the underlying Anthropic / OpenAI calls. Structural capture, not just a timeline.
Code
rag-optimized AI Tooling
An observable, optimized RAG pipeline with a web UI, real span tracing and guardrails, a one-click Render deploy, and a no-API-key demo mode. Includes a LoRA Lab that fine-tunes a tiny adapter in pure NumPy (hand-written gradients) live on free-tier hardware.
Code
Brain Modulyzer Research Software · UC / LBNL licensed
A hierarchical visual exploration technique for fMRI data — the system behind an IEEE TCBB '16 paper. Licensed by the University of California through Lawrence Berkeley National Laboratory.
Code IEEE TCBB '16 Video
ECoG Cluster Flow Research Software · Best Paper ACM-BCB '16
Interactive spatio-temporal cluster analysis of electrocorticography data — Best Paper at ACM-BCB '16, extended in BMC Bioinformatics '17. Licensed by the University of California through Lawrence Berkeley National Laboratory.
Code ACM-BCB '16 BMC '17
06

Technical Writing

Twenty interactive essays, organized as five short series — read any one alone, or follow a series top to bottom. Earlier long-form work lives on Medium.

Series 1 · Building agents that finish

Why long tasks fail and the machinery that fixes it — pacing, memory, forgetting, rollback, and the loop itself.

Agents Your AI Agent Is a Marathoner, Not a Sprinter
Long-horizon agents fail like marathoners, not sprinters — a playbook on compounding error, context rot, pacing, checkpoints, context resets, and sub-agent relays, backed by a 20,000-trial simulation.
Agent Infra · Interactive Agents Can Sprint. Memory Lets Them Run Marathons.  ·  New & interactive
The sequel to the marathon post: the baton itself. Models sustain 30+ hour tasks but every context window still gets wiped — why agent memory and its deployment is the whole ballgame, via Anthropic’s long-running harness and Nous Research’s self-correcting Hermes — with a live "memory relay" simulation you can steer (failure rate, context size) and the design-review checklist.
Agent Memory · Interactive Your Agent Has a Filing Cabinet. It Needs a Hippocampus.  ·  New & interactive
Agents get one flat memory store; cognition runs four — working, episodic, semantic, procedural — wired by consolidation during sleep. The architecture mapped to agent infra (MemGPT, Generative Agents, Voyager assembled into one design), retrieval as ranking, forgetting as precision — and a live consolidation lab: 14 simulated days where the agent that sleeps ends ~50 points ahead of the one that hoards.
Agent Infra We Gave Agents Memory but No Way to Forget  ·  New & interactive
“Agent memory” is usually append-everything retrieval — and it makes agents worse over time. Why real memory needs forgetting, with a live in-browser simulation and a Colab notebook.
Agent Infra We Gave Agents Tools but No Undo Button  ·  New & interactive
Without rollback, long agents don’t just fail — they finish and corrupt state. The database wisdom that fixes it — checkpoints, idempotency, compensation — with a live simulation and a Colab notebook.
Agent Infra · Interactive The 30-Hour Agent Is an Infrastructure Problem.  ·  New & interactive
The loop as an operating system: context as RAM (compaction high-water marks, KV-cache discipline, spill-to-disk), tokens as the meter (hierarchical budgets, circuit breakers), watchdogs + Erlang-style supervision, and an eval pyramid for runs too long to rerun — with a live run console where toggling compaction, watchdog, or checkpoints decides whether a simulated 30-hour run survives.
Series 2 · Knowing if they're any good

Evaluation and trust — from grading traces to catching gamed metrics to deciding when an agent may act alone.

Agent Evaluation · Interactive · D3 Six Agents Finish the Same Task. The Trace Knows Who’s Better.  ·  New & interactive
Six differently-scaffolded agents, one task, same harness — an answer-only judge calls it a six-way tie while the traces blow them apart. A trace-metric framework (recall@K, progress-AUC, loop rate, verification, pass^k), behavioral clustering with kNN drift alarms, and a live D3 fingerprint lab that runs the whole experiment in your browser.
Evaluation You’re Grading Your AI on the Wrong Test  ·  New
A benchmark win isn’t a model that works — a playbook on eval variance, contamination, biased LLM judges, and reliability@k, backed by a 20,000-trial simulation of how grading method beats raw model quality.
Self-Improving Systems · Essay Catching Goodhart in the Act  ·  New & interactive
I let a model improve itself against its own grader and watched the score climb while held-out truth quietly fell. Divergence-onset monitoring caught the gaming within 2–11 generations in 100% of gamed runs — with a live simulation and the "verifier half-life" playbook.
Agentic AI · Report Fifteen Domains, One Wall: The Verification Gap  ·  New
Read agentic AI across fifteen domains at once and the same wall appears in every one. Why the bottleneck was never generation — it’s verification — and where value migrates next: the “Trust Stack.”
Agent Autonomy · Interactive · D3 Autonomy Is a Dial, Not a Switch.  ·  New & interactive
When should an agent ask, tell, or just act? An expected-loss framework (confidence × stakes × reversibility), a per-task-class trust ratchet, escalation mechanics that prevent rubber-stamping — and a live policy observatory: 400 streaming decisions, draggable thresholds, and a Pareto frontier showing exactly where your policy sits between interruptions and catastrophes.
Series 3 · Interfaces: tools, pictures, generated UI

The surfaces agents touch and produce — tool contracts, visualization as infrastructure, and answers that render.

Agent Infra · Interactive Your Agent Isn’t Dumb. Its Tools Are.  ·  New & interactive
Most “agent failures” are interface failures: a tool definition is a prompt the agent re-reads at every decision point. The seven sins of tool design (ambiguous names, kitchen-sink params, unbounded responses, dead-end errors…), a per-tool eval loop — and a live grader that scores any MCP / function-calling JSON on 8 dimensions as you type.
Visualization × Agents · Interactive Agents Became Systems. Nobody Drew Them.  ·  New & interactive
We debug distributed systems by scrolling JSONL. A five-layer framework for visualization across the agent lifecycle — trace waterfalls, behavior fingerprints, workflow flows, live architecture maps, deployment dashboards — grounded in Shneiderman / Tufte / Munzner, with a live D3 control room: plug the Planner, Memory, and Verifier in and out of a running agent system and watch the consequences flow.
Generative UI · Live Demo Your Agent Answers in Paragraphs. It Should Answer in Interfaces.  ·  New & live demo
Generative UI: agents that render the tool you needed instead of describing it. The specs-not-pixels architecture, UI components as tools, evals for interfaces — and a fully working playground in the post: type a request, watch intent → spec → validate → render light up, then use the generated charts, forms, trackers and timers. Edit the spec JSON, watch the UI rebuild.
Field Report · Interactive The Last Click  ·  New & live trace
An agent fixed a real open-source bug in forty minutes. Shipping it took five hours, two agent sessions, four permission walls — and exactly one human click. The complete trace of a real contribution, rendered as a live span waterfall next to its no-walls counterfactual, and the design lessons: prepared artifacts, legible denials, consent as the interface.
Series 4 · Strategy & economics

Where the durable value sits — the harness over the model, domain depth over generality, and the real cost of more agents.

Agent Strategy · Interactive The Model Is a Guest. The Harness Is the House.  ·  New & interactive
You’ll swap models five times and your product will still be itself — identity lives in the harness. A razor for what survives each swap (model-shape depreciates, world-shape compounds), the rehearsed swap protocol, the bitter-lesson counterargument taken seriously — and a live simulator: 36 months, six model generations, the moment the system detaches from its own model.
Agent Strategy · Interactive The Next Million-Dollar Agent Is Boring and Domain-Specific.  ·  New & interactive
General agents demo; domain agents invoice. The full playbook: collect & curate expert data into one corpus that compiles to three artifacts, climb the training ladder (scaffold → SFT → DPO → distill), answer by K verified paths with a judge, gate everything on a golden eval set, deploy on a trust ratchet — with a live multipath explorer showing what each extra path buys.
Multi-Agent · Report More Agents Isn’t Better: The Coordination Tax  ·  New
Two frontier labs reached opposite conclusions on multi-agent systems. The reconciliation — single strong agent by default; multi-agent only for verifiable, parallel breadth — plus the ~15× token tax and the MAST failure taxonomy.
AI Agents · Report Your AI Agent Aced the Test. It Still Can’t Do the Job.  ·  New
Capability soared while 95% of enterprise pilots returned nothing. Why reliability — not intelligence — is the wall for AI agents in 2026, and the operator’s playbook for crossing it.
Series 5 · ML foundations

The modeling layer underneath — retrieval systems and explaining what the ranker did.

Retrieval / RecSys Two Towers, One Index: How Retrieval Models & ANN Search Are Co-Designed  ·  New · interactive
A source-grounded deep dive with a drag-to-explore demo: the two-tower model and approximate nearest neighbor search are one co-designed system, not two. From DSSM and the logQ correction to HNSW, IVF-PQ and ColBERT — and how the exact same machine powers recommendation feeds. Assembled by a fact-checked multi-agent research pass.
Explainability Why Did You Rank That? Explainability for LLM-Powered Retrieve-and-Rank  ·  New
A method-by-method field guide to explaining the four-stage ranking funnel — SPLADE/ColBERT structural readouts, RankingSHAP, activation patching, faithful logit signals, counterfactual stage ablation — and the one rule underneath them all: plausible is not faithful. Fact-checked multi-agent research pass.
Earlier writing · Medium
Explainable AI for Deep Learning Interpretability
Designing deep learning models is hypothesis-driven; interpretability is key to trustworthy models — the Achilles' heel of deep neural networks.
Linear Regression from Scratch Foundations
An attempt to clearly explain the simplest ML algorithm in Python — predicting a linear relationship between inputs X and an output Y.
Neural Networks in Organizations Deep Learning
Neural networks are now ubiquitous — convolutional, recurrent and beyond — with manifold applications across medicine, transportation, and visualization.
Qualitative Methods to Evaluate ML Evaluation
The importance of visual analytics in machine learning, as ML methods play an increasingly influential role in the world.
Impact of Methods in Network Science Network Science
Transportation, brain, and social networks all rely on machinery from graph theory and data visualization.
07

AI Infrastructure & Experience

Where the models meet production — experience across industry research and the infrastructure that scales AI systems.

Experience
  • Staff ML Engineer / Scientist — Intel / Intuit
    Building and shipping LLM-powered recommendation and agentic-AI systems in production. Also DeepInsight — a real-time ML analytics engine for network understanding (C++, Python, Kubernetes, Kafka, GoLang, TensorFlow, Apache Flink, ML anomaly detection).
  • Research Engineer — Samba TV
    Co-creator of Sambavision — applied ML/CV research shipped into product.
  • Research Intern — Adobe Research
    Interpretable deep learning — DeepCompare, for comparing and debugging deep models (patent + IEEE CG&A).
  • Graduate Fellow — Lawrence Berkeley National Lab
    Computational Research Division — large-scale scientific data + ML.
Education
Infrastructure & Scale

The systems work behind the models. At Intel / Intuit I help build DeepInsight, a real-time ML analytics engine — streaming pipelines on Kafka and Apache Flink, services in C++ / GoLang / Python on Kubernetes, with ML anomaly detection. The same instinct runs through my open-source work: distributed training (DeepSpeed / FSDP / DDP), inference serving, and agent observability — infrastructure in service of shipping and scaling AI systems.

20+
Open-source AI projects
8
Peer-reviewed papers
150+
Citations
5M+
Users in production
08

Publications

Peer-reviewed research — modelling data through mathematical models and visualization, with a Best Paper award and a patent.

Netostat: Analyzing Dynamic Flow Patterns in High-Speed Networks
Cluster Computing
PDF
State-Based Similarity Visualization
Information Visualization
PDF
Interactive DeepCompare Model Analysis: Comparing Deep Learning Models
IEEE Computer Graphics and Applications
PDF
Interactive Model Analysis for Deep Learning
Patent at Adobe Systems
PDF
PhD Dissertation: Visual Analysis Methods for Static and Dynamic Networks
University of California, Davis & Lawrence Berkeley National Laboratory
Author: Sugeerth Murugesan
PDF
Brain Modulyzer: Interactive Visual Analysis of Functional Brain Connectivity
IEEE Transactions on Computational Biology '16
Sugeerth Murugesan, Kristofer Bouchard, Edward Chang, Max Dougherty, Bernd Hamann, Gunther H. Weber
PDF Code Video BibTeX
Hierarchical Spatio-temporal Visual Analysis of Cluster Evolution in Electrocorticography DataBest Paper
ACM-BCB '16 — 7th ACM International Conference on Bioinformatics, Computational Biology
Sugeerth Murugesan, Kristofer Bouchard, Edward Chang, Max Dougherty, Bernd Hamann, Gunther H. Weber
PDF Code Video Talk BibTeX
Multi-Scale Visual Analysis of Time-Varying Electrocorticography Data Via Clustering of Brain RegionsInvited Best Paper
BMC Bioinformatics '17
Sugeerth Murugesan, Kristofer Bouchard, Jesse A. Brown, Bernd Hamann, William W. Seeley, Andrew Trujillo, Gunther H. Weber
PDF Code Video Talk BibTeX
09

Skills

Organized for AI research engineering. Highlighted skills are where I do my deepest work.

AI & Machine Learning
LLM Post-Training (DPO / GRPO / RLHF) LoRA / QLoRA Fine-Tuning Transformers Generative AI Multimodal (VLMs) Graph Neural Networks Recommendation Systems PyTorch TensorFlow
Research & Evaluation
LLM-as-Judge Evaluation Eval Harnesses & Benchmarks Experiment Design & Ablations RAG Evaluation Quality / Cost Pareto Analysis Hyperband / HPO Reproducible Experiments
Systems & Infrastructure
Distributed Training (DeepSpeed / FSDP / DDP) Inference Serving (vLLM / SGLang) Agent Observability & Tracing Real-Time ML Pipelines ML Anomaly Detection
Programming
Python C++ GoLang TypeScript / JavaScript SQL
Cloud & GPU
GPU Training (CUDA / MPS) Colab / Kaggle AWS GitHub Actions / Pages
Cloud & GPU in service of training and serving models.
Distributed Systems
Kafka & Apache Flink (Streaming) Kubernetes Apache Beam Scalable Serving
Used to scale data and AI workloads — the plumbing behind production ML.
10

Contact

The fastest ways to reach me and see the work.

Get in touch

I'm always happy to talk about LLM post-training, agent evaluation, RAG, and the infrastructure that scales AI systems. Email is best — or browse the code on GitHub.

sugeerth@gmail.com GitHub LinkedIn Google Scholar Medium
Open to ML & Research Engineer opportunities