Currently building multi-agent systems ● QEMA-G published on Zenodo ● The Coin in the Air - out now on Amazon ● VP of R&D, AI Skunkworks @ Northeastern ● Open to Co-op / Internship & Full-Time roles - starting immediately ● Open to relocation · Boston, MA · remote US ● 30+ open-source repositories ●
Open to roles · starting immediately multi-agent · RAG · RL QEMA-G · published on Zenodo open to relocate

AI Engineer · Researcher · Author

Most engineers ship code. I ship research that ships back. Author of QEMA-G, a quantum-enhanced memory framework for graph AI published on Zenodo, and of The Coin in the Air, a book on quantum machine learning out now on Amazon. VP of R&D at AI Skunkworks, the graduate research org I rebuilt at Northeastern. Four years of production engineering, now building the layer where multi-agent systems, RAG, and reinforcement learning converge into LLMs that do useful work in the real world.

Aravind Balaji
4+Years industry experience 3.90/4GPA at Northeastern 30+Open-source repositories 1stPlace, MGEN Hackathon 2025
Selected Work

Things I've built.

Multi-agent systems with statistically validated evaluation, RL-driven orchestration, fine-tuned models, and production data platforms. Each one shipped, tested, or published - not a tutorial follow-along.

Multi-Agent · Security · Open-Core Product

CodeSentinel v2 - AI Code Security Review

Citation-grounded multi-agent review: three specialised agents ground every finding in a 70-passage OWASP Top 10 2025 / CWE knowledge base, with an adversarial evaluator over each claim. 97% fewer hallucinated findings (FPR 0.789 → 0.111, McNemar's p = 0.0312) vs. a single-prompt baseline - same model, same prompts, different architecture. Ships as CLI, REST API, SARIF 2.1.0, Docker/Helm.

Multi-AgentRAGSARIFDockerHelmClaude
Reinforcement Learning · Agentic AI

RL-CodeSentinel - Reviewers That Learn

Layers a UCB-1 contextual bandit (per-code-type agent configuration) and REINFORCE policy gradient (2,853-param MLP for finding synthesis) onto the CodeSentinel pipeline, so review quality improves with developer feedback: +28.1% mean reward vs. random baseline across 200 episodes × 5 seeds (95% CI [25.6%, 30.7%]).

UCB-1REINFORCELangGraphMulti-AgentPython
Multi-Agent · Evaluation-First

CEREBRO - AI Research Assistant

3-agent CrewAI + n8n hybrid with a 940-line custom tool querying 16 academic databases in parallel. Achieved 85% source relevance (+27 pts over web-only baseline), 90% factual consistency, and 95% citation completeness across 45 evaluation runs - peer-validated at Cohen's κ = 0.74.

CrewAIn8nPythonStreamlitEvals
Agent Infrastructure · Knowledge Graphs

Foglight - Internet Intelligence for Agents

An all-seeing intelligence layer: pluggable ingestion channels normalized to one schema, persistent memory, a temporal knowledge graph, watchlists with alerts, and cited brief synthesis. Exposed as CLI, REST API, and MCP server so both humans and agents can consume it - with a dependency-free offline core.

MCPKnowledge GraphPythonREST APIAgents
Published Research · Quantum AI

QEMA-G - Quantum-Enhanced Memory for Graph AI

Theoretical framework integrating quantum memory architectures with graph neural networks to attack the memory-wall problem in large-scale GNN training. Author: Aravind Balaji · Co-author: Prof. Nik Bear Brown. Published on Zenodo, with a Qiskit reproduction suite covering noiseless and IBM-Brisbane noise models.

QuantumQiskitGNNResearch
Systems · Rust · Aerospace

Orbistra - Space Operations Platform

Tracks the live public space catalog (~16,000 objects): parallel SGP4 propagation in Rust (full catalog in milliseconds), three-stage conjunction screening with collision-probability estimation, an axum REST API, and a real-time 3-D operations console. Screens 16k objects × 6h in about a minute on a laptop.

RustSGP4axumThree.js
AI Trust Layer · Formal Methods

Verimathix - Verified Math for LLMs

LLMs win IMO gold yet still ship confidently wrong math. Verimathix is the trust layer: step-level verification with first-error localization (SymPy symbolic + numeric probing), natural-language → Lean 4 autoformalization, reference numeric kernels, and a step-grading benchmark harness with CI.

SymPyLean 4NumPyBenchmarks
LLM Fine-Tuning · QLoRA

QueryCraft - Natural Language to SQL

Fine-tuned TinyLlama-1.1B with QLoRA on the Spider dataset for NL-to-SQL generation - 100% improvement on SELECT-clause generation against the base model. Shipped with a ChromaDB RAG retrieval layer over schema metadata and a Gradio demo.

TinyLlamaQLoRAChromaDBRAGGradio
Healthcare · Knowledge Graphs

MediGraph AI - Clinical Knowledge-Graph Platform

Offline-first clinical knowledge-graph and decision-support platform with FHIR / HL7 / C-CDA connectors for US + India. Graph-aware RAG: Neo4j retrieval, structured reasoning, and natural-language explanations of clinical relationships over Snowflake-hosted data.

Neo4jFHIRLangChainRAGSnowflake
Cloud Engineering · GCP

Robust Data Processor - Multi-Tenant Ingestion

Fault-tolerant ingestion pipeline, deployed live on GCP: Cloud Run API with instant 202 acks → Pub/Sub buffering → workers with retries and dead-lettering, per-tenant Firestore isolation, PII redaction, and load testing.

GCPCloud RunPub/SubFirestorePython
Full Portfolio

Everything else on GitHub.

30+ open-source repositories across agentic AI, domain intelligence platforms, and production systems.

Python · OSINTWardSight

Intelligence-fusion platform with a citation-grounded AI analyst copilot - ADS-B/AIS/GDELT fusion, entity resolution, anomaly detection.

Java · HealthcareClearAuth

CMS-0057-F prior-authorization platform - FHIR-native PAS intake, auditable adjudication, SLA enforcement, CMS PA metrics.

Python · ClimateCarbonoscope

Open climate intelligence: auditable GHG accounting, Climate TRACE analytics, grid carbon forecasting, disclosure parsing.

Python · AgTechAgroCortex

AI cortex for agriculture: LLM benchmark, plant-disease vision, satellite field analytics, citation-grounded AI agronomist.

Python · Civic TechCiviSynth

Political intelligence platform: narrative tracking, RAG fact-checking with evals, legislative intelligence, election forecasting.

Python · RAGOmniCanon

Citation-verified AI for sacred texts - multi-faith corpus, zero-hallucination RAG, TheoBench LLM benchmark, canon-aware OCR.

Python · Sci-MLPhysWeave

Physics simulation meets ML: differentiable simulation, neural PDE surrogates, stochastic finance, quantum circuits, molecular dynamics.

Python · ChemistryAlcheMind

De novo molecular discovery: RDKit + genetic generation + ML property prediction + FastAPI, end to end.

Python · RoboticsEveryCam

Every camera is a robot teacher - privacy-first, robot-ready embodied data from everyday cameras.

Go · COBOL · FinTechQuantumTeller

The open-source ATM stack: ISO 8583 switch in Go + COBOL core banking + roadmap to ML fraud scoring and post-quantum crypto.

TypeScript · Full-StackServiQue v2

Production-grade service booking platform - Node + TypeScript + Express + Prisma API, React SPA, JWT/RBAC, tests, Docker, CI.

Python · Edge AISmart Trolley

Edge-AI shopping trolley on Raspberry Pi - VGG16 → MobileNetV3 TFLite INT8 produce recognition, load-cell weighing, Firebase billing.

React · 1st PlaceDNATE MSL Practice Gym

1st place, MGEN Hackathon 2025 - AI conversation simulator for Medical Science Liaisons (React, Node.js, OpenAI API), built end-to-end in 48 hours.

Jupyter · RLLLM Agents & Deep Q-Learning

LLM agents and DQN experiments on Atari games - classic RL meets modern agent tooling.

MERN · HealthcareCareHub

Hospital management system - MERN stack with JWT authentication and role-based access control.

HTML · GamesCheese Chase Arcade

Ten arcade games + a 10-chapter story mode in a single HTML file. Zero dependencies.

HTML · AuthorIdeas You Can Picture

Official website for my book series explaining quantum computing and AI with zero equations.

GitHub…and more →

The full list - 30+ repositories, updated constantly.

Experience

Where I've shipped.

Four years across healthcare technology, cloud migrations, and SaaS reliability before grad school - shipping in production, not just classrooms.

May 2025 - Present · Northeastern

Vice President of Research and Development

AI Skunkworks · Advisor: Prof. Nik Bear Brown
  • Rebuilt the graduate AI research organization from the ground up; authored the constitution and secured formal recognition by Northeastern's Graduate Student Government
  • Recruit and mentor graduate researchers across multi-agent systems, RAG, and applied LLM research
Jul - Dec 2024 · Chennai

Senior Software Engineer

HealthTech International
  • Built AI-assisted NLP workflows in Python to classify and extract insights from large-scale healthcare documents
  • Automated data ingestion and reporting pipelines: manual processing effort down 60%
  • Shipped systems serving 100+ daily clinicians in a production EMR environment
Jun - Dec 2022 · Chennai

Data Scientist Intern

Futurenet Technologies
  • Analyzed 10,000+ daily system events with Python; built automated reporting pipelines cutting time-to-insight
  • Supported AWS/Azure cloud migration covering 5,000+ records; Splunk ML pipelines contributed to 27% lower downtime
Jun 2021 - May 2022 · Bengaluru

Software Engineer Intern

Checkpoint Systems
  • Enterprise SaaS for retail supply chains across 50+ enterprise clients; shipped 20+ fixes, customer-reported issues down 12%
Award · Northeastern University

1st Place, MGEN Hackathon 2025 - DNATE MSL Practice Gym

Led a 4-person team to first place, building an AI conversation simulator for Medical Science Liaisons (React, Node.js, OpenAI API) end-to-end in 48 hours.

GitHub ↗
Stack

What I build with.

Deep on AI/ML and Python; fluent across the data, cloud, and full-stack layers needed to ship end-to-end systems.

AI & Machine Learning

Multi-Agent SystemsLangGraphCrewAIMCPRAGQLoRA Fine-TuningReinforcement LearningPyTorchHugging FaceAnthropic APIOpenAI APILLM EvalsPrompt Engineering

Languages & Frameworks

PythonTypeScriptJavaScriptJavaSQLReactNode.jsFastAPIExpressStreamlitGradio

Data & Cloud

GCPAWSAzureCloud RunPub/SubNeo4jChromaDBPostgreSQLMongoDBSnowflakeDockerHelmCI/CD

Research & Quantum

QiskitPennyLaneKnowledge GraphsGNNsLean 4SymPyStatistical EvaluationTechnical Writing
Education
2025 - 2026

Master of Science in Information Systems

Northeastern University, Boston · GPA 3.90/4.0 · Expected Dec 2026

2021 - 2023

Master of Technology in Software Engineering

BITS Pilani, India

2016 - 2020

Bachelor of Technology in Electrical, Electronics and Communication Engineering

SRM Institute of Science & Technology, Chennai

Research & Publications

Research that ships back.

Peer Repository · Quantum AI

QEMA-G: Quantum-Enhanced Memory Architectures for Graph-Based AI Systems

Aravind Balaji, Nik Bear Brown · Northeastern University. A theoretical framework with feasibility analysis, published on Zenodo - plus an open Qiskit simulation suite reproducing every numerical result under noiseless and IBM-Brisbane noise models.

Textbook Contribution · Forthcoming 2026

Design of Agentic Systems with Case Studies

Contributor to Prof. Nik Bear Brown's textbook on agentic systems: retrieval-augmented generation as an evidence layer for LLM agents, evaluation methodology for citation faithfulness, and production case studies.

The Book

Out now on Amazon.

Book 1 of Ideas You Can Picture - a six-book series explaining quantum computing and AI with clear pictures and not a single equation.

The Coin in the Air - book cover
Book 1 · Out Now

The Coin in the Air

Quantum Machine Learning You Can Picture

Quantum computing may be the most exciting idea of our time - and the most badly explained. Through one simple, unforgettable image - a coin spinning in the air - you'll finally understand superposition, entanglement, interference, and the new kind of AI they're being turned toward. 27 commute-sized chapters. Zero math. No background required.

Five more books in the series are on the way, covering quantum cryptography, quantum hardware, and modern AI.

Writing

Words & ideas.

Narrative nonfiction on AI engineering, quantum computing, and the human side of the systems we build - published on Substack and Medium.

Beyond the code: I also produce independent music with AI tools - same loop as engineering: idea → prototype → critique → ship.

Contact

Hire someone who ships AI, code, and research.

Most candidates pick a lane - production engineering or research, models or systems, theory or shipping. I'm fluent in all three, which is the rarer profile, and the one that makes AI initiatives actually move.

Open to: AI / ML Engineering · Applied Research · Multi-Agent Systems · Data & ML Platforms · Full-Stack with an AI layer

When: Open to Co-op / Internship & Full-time roles - starting immediately. No visa sponsorship required.

How: In Person, Remote or Hybrid. Where: Boston, Anywhere in the United States and around the world.