Resume

Abhinav Karthik

AI Engineer · Boston, MA

Summary

Master's in AI from Northeastern (4.0), computer engineering from UMass Amherst. I've shipped a long-term memory system for a commercial agent, an optimizer that schedules a cardiovascular service line, and a Battleship engine that beats a record that stood since 2011.

Experience

Jun 2026 — Now
Boston, MA
AI Engineer · State Street via Xoriant
- Building LLM-driven contract analysis and extraction workflows on Evisort for a global custodian bank.
- Retrieval, extraction and evaluation work so legal teams can trust what the model says about a document.
Jan 2026 — Now
Portland, ME
AI Research Engineer · MaineHealth · Roux Institute
- Built a mixed-integer linear programming system that generates annual schedules for ~60 physicians across 5 subspecialty groups and 46 services.
- Designed a cascading multi-stage solver on Google OR-Tools CBC with a registry-based constraint engine supporting 14 configurable hard and soft constraint types.
- Block variable compression, per-group skeleton decomposition and upstream-aware constraint propagation: 91% happiness score across 8,500+ weekly assignments in under 4 minutes.
- Shipped it as a Flask web app with drag-and-drop pre-filled uploads, live solve progress and Excel export for clinical deployment.
Mar 2026 — Now
Boston, MA
Lead Engineer · 7D Connect · Northeastern
- Architected a Next.js 16 monorepo where one web app serves the admin UI and the mobile REST API over a single Prisma/PostgreSQL schema.
- Native SwiftUI and Kotlin/Compose driver apps: route start/finish, GPS-stamped attendance, inspection checklists, incident reports and mileage.
- Role model spanning super admin, vendor admin, district and driver, with vendor impersonation for support and nightly backups.
Jun 2025 — Sep 2025
Boston, MA · Hybrid
AI Engineer · EasyBee AI
- Architected a persistent long-term memory system for the primary commercial agent, lifting retention by 15%.
- Cut agent latency by ~2 seconds through empirical evaluation and context engineering.
- Led an agentic coding team that delivered an admin dashboard with deep-research capabilities in under two weeks, plus an automated RAG knowledge-base pipeline with industry-specific chunking metadata.
- Built an MCP-based extension for omni-channel SMS and WhatsApp messaging via Twilio while preserving context and memory.
- Drove an AI-first initiative automating repeatable work across business and technical teams, averaging a 3.5× productivity gain.
Jan 2021 — May 2024
Bangalore, India
Founder · BucketListEr
- Conceptualised, built and released the app; connected users with like-minded people and partners offering discounts.
- Hired and ran two intern teams (investor search, marketing) at near-zero cost.
Jun 2024 — Jul 2024
India
IT Intern · SFJ Business Solutions
- Wrote the sections of a Python, Pandas and MATLAB testing tool that measured algorithmic speed and surfaced sub-optimal paths.

Research

2026
under review
GA-tuned ensemble agent for Battleship
Four Battleship strategies, one heatmap each, blended by weights a genetic algorithm learned. Averages 40.5 moves to win and beats the 2011 benchmark.
with Jonathan Mwaura
2026
under review
Adaptive generational ↔ steady-state switching for GAs
A genetic algorithm that starts generational, watches its own elite centroid, and switches itself to steady-state the moment exploration stalls. No hand-picked switch point.
with Jonathan Mwaura

Selected projects

2026 – now
Legal intelligence at State Street — What I do now: LLM workflows for contract intelligence on Evisort.
2026
Luna OS — An LLM-native operating system shell built with Tauri and React.
2026
Genome Explorer — A 3D DNA helix you can orbit, where the pathogenic variant glows at 60 bpm.

Education

Sep 2024 — May 2026
Northeastern University — M.S. Artificial Intelligence · GPA 4.0 / 4.0
Jun 2020 — May 2024
University of Massachusetts Amherst — B.S. Computer Engineering · Phi Delta Theta, founding member & VP

Skills

Agents & LLMs
Claude Code · Codex · Cursor · MCP · LangGraph · LangChain · RAG · Vector DBs · Prompt engineering · Fine-tuning · Evals · Voiceflow
ML & RL
PyTorch · TensorFlow · Keras · scikit-learn · OpenCV · PPO / MARL · CNNs · Transformers · Pandas · NumPy
Optimisation
Genetic algorithms · OR-Tools · MILP · Monte Carlo · Bayesian optimisation · Constraint programming · Information theory
Languages
Python · TypeScript · Java · C++ · C# · Embedded C · MATLAB · Swift · Kotlin
Web, mobile & infra
Next.js · React · Tauri · SwiftUI · Jetpack Compose · Flask / FastAPI · PostgreSQL · Prisma · Supabase · Pinecone · Docker · AWS · Vercel · Twilio

Certifications

Generative AI with Large Language Models — DeepLearning.AI × AWS, 2024
Generative AI: Prompt Engineering Basics — IBM, 2024
Python for Data Science, AI & Development — IBM, 2024