AI Engineer

PyTorchLangGraphFastAPIDockerK8sPostgreSQL

Open to Full-Time AI/ML Roles · Available Now

Madhavan
Balaji.

AI Engineer · MS CS @ Indiana University

I build and ship production AI systems: LLM pipelines, computer vision models, and the ML infrastructure that runs them at scale. Research-backed, engineering-disciplined.

View Work Resume ↗

LinkedIn GitHub Medium 🤗HF EmailIndianapolis, IN

AI Engineer ✦ Machine Learning ✦ LLMs ✦ Computer Vision ✦ MLOps ✦ Data Science ✦ Research ✦ AI Engineer ✦ Machine Learning ✦ LLMs ✦ Computer Vision ✦ MLOps ✦ Data Science ✦ Research ✦

About

Who I Am

Background

I'm Madhavan Balaji, an AI Engineer with a Master's in Computer Science from Indiana University. I build systems that solve real problems, working across machine learning, computer vision, and applied AI to turn raw data into production-ready software.

From engineering high-accuracy visual retrieval systems and multi-label classifiers to designing end-to-end ML pipelines, I bring both research depth and engineering discipline. I've published findings, filed a patent, and shipped systems that run in production, not just in notebooks.

Beyond building, I care deeply about knowledge transfer. As a Technical Instructor at Indiana University, I helped 30+ students work through complex CS concepts with visual explanations and hands-on mentorship. Today I tutor Statistics for AI at MAC IUI.

Currently

Statistics Tutor at MAC IUI · MS CS, Indiana University, May 2026 · Open to full-time AI/ML roles

DegreeMS Computer Science

UniversityIndiana University

LocationIndianapolis, IN

FocusAI / ML Engineering

StatusOpen to Full-Time Roles

PatentPublished application, 2024

Teaching30+ students mentored

Projects10+ shipped

Technical Expertise

Comprehensive skills across infrastructure, ML/DL, LLM agents, data operations, and monitoring

Infra & MLOps

Kubernetes

Docker

Jenkins

ArgoCD

AWS

GCP

Airflow

ML / Deep Learning

Python

PyTorch

TensorFlow

Scikit-learn

C/C++

HuggingFace

LoRA

GAN

LLM & AI Agents

LangGraph

CrewAI

Ollama

ChromaDB

LanceDB

CLIP

BLIP-2

Stable Diffusion

DataOps & Versioning

DVC

PostgreSQL

Redis

MySQL

Git

DuckDB

Polars

Monitoring & Serving

Prometheus

Grafana

FastAPI

Flask

Streamlit

React

Evidently AI

Experience

Professional Journey

Teaching, tutoring, and applied ML work

Aug 2026 – Present Indianapolis, IN● Current

StatisticsProbabilityHypothesis TestingRegressionTutoring

Statistics Tutor (Statistics for AI)

MAC IUI

Statistical Foundations: Teach statistics for AI, covering the statistical foundations behind machine learning: probability, distributions, hypothesis testing, confidence intervals, and regression.
Concepts to AI Practice: Connect each statistical concept to its AI use, such as regression as a predictive model and hypothesis tests and confidence intervals for judging model results.
Communication: Explain quantitative concepts in clear written and verbal form, adjusting to each student's level.

Aug 2025 – Dec 2025 Indianapolis, IN

AlgorithmsDynamic ProgrammingGraph TheoryMentorshipCurriculum Design

Technical Instructor & Curriculum Lead

Indiana University

Education Contributions: Designed and delivered weekly technical workshops on Algorithms & Optimization to 30+ students, breaking down complex logic (Dynamic Programming, Graph Theory) into intuitive visual explanations.
Mentorship: Guided students in refactoring and optimal design patterns, mirroring Developer Relations (DevRel) responsibilities by debugging user issues and bridging knowledge gaps.
Community Building: Established a community-first mentorship and peer-review system to drive engagement, demonstrating the ability to build and sustain a technical community.

Madhavan teaching at an Algorithms workshop, LeetCode problem projected on screen

Weekly Algorithms workshop · Indiana University, 2025

Teaching is the most efficient form of learning I've encountered. Every whiteboard session, watching a student's face shift from confusion to clarity on dynamic programming, sharpened my own understanding in ways that hours of solo study never could.

When I started leading weekly workshops on Algorithms & Optimization, I assumed I was there to give knowledge. What I didn't expect was how much I'd receive in return. Students ask the questions that textbooks skip: the "but why does this work?" questions that expose the gaps in your own mental model. Answering those questions live, at the whiteboard, forced me to rebuild my understanding from first principles. I stopped thinking in code and started thinking in structure.

Over dozens of sessions covering Graph Theory, DP, and Greedy algorithms, I developed a discipline I now carry into every engineering context: the ability to explain precisely, not approximately. That precision, earned through teaching, makes me a better collaborator, a cleaner code reviewer, and a sharper problem-solver.

Teaching DP exposed my own gaps

Every time a student asked "but why does the subproblem boundary work here?", I had to rebuild my mental model from scratch, and came out sharper each time.

Graph Theory via whiteboard, not slides

Drawing BFS/DFS live forced me to develop spatial intuition I never got from textbooks. Visual teaching is fundamentally different from visual learning.

Diagnosing mental blockers

A student's confusion is a diagnostic signal. Learning to read it made me a better debugger, interviewer, and communicator on engineering teams.

Weekly prep accelerated my fluency

Preparing workshops 2–3x per week compounded: I solved more LeetCode problems in one semester of teaching than in any prior year of solo study.

Sep 2022 – Nov 2022 Bangalore, India

PythonComputer VisionImage ProcessingDeep LearningData Analysis

Data Analyst Intern

Coincent

Inference Optimization: Engineered feature extraction pipelines using advanced image processing, reducing latency by 30% for real-time computer vision performance.
Model Development: Developed an end-to-end visual retrieval system achieving 90% accuracy, effectively translating raw visual data into a functional visual search engine.
Recommendations: Built multi-label classifiers for 1,000+ distinct classes, optimizing personalized style recommendations through deep learning retrieval logic.

Projects

Featured Work

14 projects spanning autonomous agents, computer vision, data pipelines, and production ML

Auto-Patch, Human GatePython

Sovereign SRE

Detect → Diagnose → Fix → Deploy, all without paging anyone.

Production-grade autonomous SRE platform on 13 AWS services. CloudWatch alarms trigger a LangGraph + CrewAI multi-agent pipeline that diagnoses incidents with codebase-aware RAG (pgvector), generates patches via Amazon Bedrock, and deploys only after human approval via Step Functions + SNS. Live on AWS Amplify.

LangGraphAmazon BedrockAWSCrewAI

View Details

Found 10× Cheaper ModelPython

LLM Eval Harness

Benchmark any LLM across latency, accuracy, hallucination, and cost, in one automated pipeline.

Production-grade benchmarking framework that evaluates OpenAI, Anthropic, and Groq models simultaneously across latency (p50/p95/p99, TTFT), accuracy (semantic similarity, LLM-as-judge), hallucination (NLI cross-encoder), cost, and RAGAS metrics, with Rich terminal output, self-contained HTML reports, and a Streamlit comparison dashboard.

LLM BenchmarkingRAGASStreamlitAsync

View Details

15ms p50 RetrievalPython

DocuMind

Multi-agent research that reads your documents and writes cited reports, in seconds.

Enterprise-grade multi-agent RAG research platform on AWS. LangGraph orchestrates a 4-agent CrewAI pipeline (Researcher → Analyst → Writer → Critic) that produces fully cited reports using hybrid pgvector + BM25 retrieval with CrossEncoder reranking. Deployed on EC2 behind CloudFront with RDS PostgreSQL, Step Functions, Bedrock Claude Haiku, and Claude Desktop MCP integration.

Multi-AgentRAGLangGraphAWS Bedrock

View Details

<60s Drift DetectionPython

Project Aegis

A self-healing data pipeline that detects drift and repairs itself, before your models silently fail.

Self-healing data quality system that automatically detects and repairs data drift using Evidently AI and DuckDB streaming. Scales from cloud (200MB) to local (100GB+) with a hybrid architecture and Streamlit dashboard.

DuckDBEvidently AIPolarsStreamlit

View Details

56–75% Faithfulness DropJupyter Notebook

Chain-of-Thought Faithfulness

Does your LLM's reasoning actually drive its answers? The data says: probably not.

Research into whether LLM chain-of-thought reasoning actually influences predictions using Negative Preference Optimization. Found fine-tuning on high-quality CoT reduces faithfulness by 56–75%, a data curation problem, not training.

LLMsNPONLPResearch

View Details

Zero Training LabelsPython

VectorGaze

Natural language safety queries on live video, zero training data required.

Edge AI system detecting workplace safety violations from video using natural language queries, no training data required. Combines CLIP zero-shot embeddings, Moondream2 reasoning, and LanceDB vector search on Apple Silicon.

CLIPZero-ShotLanceDBEdge AI

View Details

80/80 Artifacts VerifiedPython

RiceFlow

Reproducible rice-genomics QC that proves every result it publishes, from laptop to AWS Batch.

CPU-only Nextflow DSL2 pipeline for rice genomic quality control using PLINK 2, BCFtools and SAMtools in Docker. Every run is fingerprinted and checksum-verified, executes locally or on AWS Batch, and publishes to a public read-only dashboard on CloudFront.

NextflowPLINK 2AWS BatchTerraform

View Details

Exactly-Once VerifiedPython

StreamCart

Joins what shoppers browsed with what they bought, in one governed lakehouse pipeline.

Retail analytics pipeline unifying live Kafka clickstream with Postgres orders in a Delta Lake medallion architecture (bronze → silver → gold), orchestrated by Airflow, modeled in dbt as a star schema, and served through a Streamlit dashboard.

KafkaSparkDelta LakeAirflow

View Details

92.4% AccuracyJupyter Notebook

DentaVision

A Vision Transformer that diagnoses dental conditions at 92.4% accuracy, in under a second.

AI diagnostic system classifying dental conditions (caries, gingivitis) at 92.4% accuracy using a pretrained Vision Transformer. FastAPI backend and React frontend deliver sub-second inference for clinical use.

ViTMedical AIFastAPIReact

View Details

<5 min Push to ProdJupyter Notebook

Hybrid Anime Recommender

A production recommender system with full CI/CD, containerization, and K8s orchestration.

Production recommender combining content-based and collaborative filtering for personalized anime suggestions. Flask API, containerized via Docker and Kubernetes, with Jenkins + ArgoCD CI/CD pipelines.

RecommenderKubernetesArgoCDMLOps

View Details

Beats Prompt-Only StylingPython

Multi-Style Image Transfer

Transforms photos into Renaissance masterpieces, Van Gogh canvases, or Impressionist works, on demand.

Transforms photos into art using GAN-based neural style transfer and Stable Diffusion with a custom Van Gogh LoRA adapter fine-tuned on 400 paintings. Supports Renaissance, Impressionism, and more.

GANStable DiffusionLoRACV

View Details

Trains 0.1% of ParamsPython

OmniBridge

Image captions that actually read the text in the image, not just describe the scene.

Vision-language captioning system built on BLIP-2, fine-tuned with LoRA on TextCaps. Generates accurate captions that incorporate visible text within images for significantly enhanced quality on text-heavy content.

BLIP-2LoRAFine-tuningVision-Language

View Details

Used in Classroom TeachingPython

LLM Inference Playground

A hands-on system that exposes what most LLM APIs deliberately hide.

Educational system exposing explicit control over transformer logit space: manual temperature scaling, top-K, and nucleus sampling without HuggingFace defaults. Tracks TTFT and throughput with a FastAPI + React interface.

PyTorchFastAPITransformersReact

View Details

~90% Lower Token CostJavaScript

Daily Tech Intel

3-tier semantic pipeline that scrapes, translates, and summarizes 100+ global tech sources daily.

End-to-end LLM application: a Cloudflare Worker fetches 10 RSS feeds (including Japanese and German sources), passes 100+ articles through Claude for semantic curation into 3 personalized sections, and caches results in Cloudflare KV. On-demand deep analysis with 7-day per-article caching. Built into this portfolio.

Claude APICloudflare WorkersRAGRSS

View Details

Patent

Patent & Research

A published patent application for an IoT system that supports elderly people living at home

PublishedIndian patent application

CareMate: An Integrated Elderly Support System

An Internet of Things system that helps elderly people live independently and safely. It brings real-time health monitoring, medication management and personalised emotional support together in one connected platform for the person, their family and their carers.

Health monitoringContinuous tracking of vital signs, with alerts when readings fall outside safe ranges.
Medication managementScheduled reminders and adherence tracking for daily medication.
Emotion detectionRecognises signs of distress or low mood so carers can respond early.
Companion assistantA conversational assistant that offers everyday support and company.

Writing

Medium Articles

@madhavanbalaji02 ↗

Oct 20256 min read

Designing with Data: How Culture, Psychology, and Big Data Shape Modern Visual Communication

Read →

Apr 20255 min read

How TSMC's 2nm Technology Will Revolutionize Machine Learning

Read →

Apr 20254 min read

From Photo to Ghibli: How AI Transforms Real Images into Studio Ghibli Magic

Read →

Deployed

Hugging Face Spaces

Multi-Style Image Transfer↗

🤗

OmniBridge Captioning↗

Live demos · Running on Hugging Face Spaces

Get in touch

Let's Work Together

Hiring for an AI/ML role, or want to talk about a project? Send me a note.

Available for opportunities

Let's Connect

Email is the fastest way to reach me. I usually reply within a day.

Live project

Daily Tech Intel

A daily briefing of AI research, industry news and global tech, curated around the topics and tools I work with. International sources are translated into English.

For You My Stack Around the World

Open Tech News