Hi, I'm Abheesht.
Software engineer building at the intersection of reliable systems and applied AI.
I care about correctness, scale, and the 3am incident that proves whether your architecture actually holds.
MS Computer Science · Arizona State University · GPA 4.0
01 / about
A bit about me
I've spent the last few years working at levels of the stack most engineers only read about.
Hardware diagnostics at Samsung. Real-time backends at a European startup. Production AI pipelines at a healthtech firm. IoT research that ended up in two IEEE publications.
That range isn't a résumé quirk — it's how I think. I'm drawn to problems that require understanding the full system, not just the layer you're hired to own.
Right now I'm most interested in roles where AI changes what a product can fundamentally do — not just automate what it already does. I want to be in the room where that architecture gets decided.
currently
MS Computer Science · Arizona State University
GPA 4.0 · May 2026
based in
San Francisco, CA
looking for
SWE · AI Engineering
anywhere
published
02 / projects
Things I've built
Agent-Techs AI Pipeline
2025Multi-agent orchestration system for healthcare document processing. Built async task queues, FAISS vector search, and deployed on GCP Cloud Run.
Text2SQL
2024Natural language to SQL translation using FLAN-T5, evaluated on the Spider benchmark with knowledge-graph-based validation for query correctness.
Scalable Graph Pipeline
2024Distributed graph data pipeline using Neo4j, Kafka, Kubernetes, and Docker. Designed for real-time ingestion and traversal at scale.
Samsung Diagnostic Tool
2023Hardware diagnostic tool for semiconductor validation in C++ and PyQt. Interfaced with I2C/SPI protocols across 3+ chip variants, including hunting down a thread contention bug.
other work
Blockchain-based agricultural supply chain tracker. Smart contracts for traceability from farm to shelf.
Real-time application context monitoring with alerting and dashboard visualization.
Time-series forecasting model for airline passenger volumes using classical ML methods.
Binary classification model to identify poisonous mushrooms from UCI dataset features.
My first real encounter with applied AI — building systems that actually shipped at a national science museum. Both papers came out of a summer at NCSM and ended up being the reason I went deeper into ML.
MusoAssist: An Interactive Virtual Bot for Museum Gallery Guidance
Humanoid chatbot deployed at NCSM Kolkata. Non-monotonic conversation chains, IoT-activated physical exhibits. 73% comprehension vs 78% with a human guide.
Low-Cost Crowd Counting for Museum Gallery Management
P2PNet CNN on existing surveillance cameras. Output drove a motorized spotlight to the most-crowded exhibit in real time. Raspberry Pi + ESP8266, no new hardware required.
03 / experience
Where I've been
Five roles across research, embedded, full-stack, and applied AI. Click any card to read the full story.
Get in touch
Let's talk
Have a role, a project, or just want to argue about system design? I'm all ears.