Education
M.S. Computer Science
Northeastern University · 2023-2026
B.Sc. Life Science (Honors) · McMaster University
About
Harshil Chudasama
Software engineer building distributed backends, applied ML systems, and end-to-end products.
I work across search and recommendation systems, Java and Spring Boot services, event-driven workflows that have to survive duplicate delivery, and performance-critical Python and C++ paths. On the ML side, quantization, ONNX serving, and the queueing math that keeps p99 honest under load.
Before engineering I worked in product management and business analysis. That's why I think in user outcomes, latency budgets, and operational tradeoffs, not just system diagrams.
Currently focused on
distributed backends
Northeastern · MS CS
Hover · 5 nearest points · illustrative of the retrieval that runs my CineMatch case study
What drives me
Products where ML reaches users at scale.
Outside of work
Training at the gym
Building a jewelry brand
Reading about markets
Exploring new cities
Tennis
Languages & Frontend
PythonC++17/20JavaGoTypeScriptSQLReact / Next.js
Search & ML Systems
PyTorchONNX RuntimeQuantizationModel servingpgvector / HNSWElasticsearch / BM25LambdaMART / LTR
Backend & Distributed Systems
Spring BootFastAPIgRPCKafkaRedisMicroservicesIdempotency / DLQs
Systems, Cloud & Performance
SIMD (AVX2)Lock-freepybind11AWS (ECS, Lambda, SQS)Aurora / PostgreSQLDockerJFR / async-profiler
Projects
Selected Work
Nine case studies across deadline-aware serving, ranking, retrieval, research tooling, and distributed backends. Click any tile for the architecture write-up and the measured results.
09 projects
01/ 09
FeaturedML & AI
Anytime Inference Planner
Deadline-Aware ML Serving
Routes each request to a profiled FP32 or INT8 variant under an M/M/c queueing bound. At 95% of pool capacity: 6.5x the deadline-goodput at 49% of the compute cost.
PythonC++ONNX RuntimePyTorchpybind11
02/ 09
Developer Tools
adduce
ML Research Artifact Auditor
A published PyPI tool that checks whether every number in a paper can still be traced to the artifact that produced it. 78 rules across 17 categories.
PythonTyperStatic analysis
03/ 09
Quant
Execution Copilot
Multi-Venue Trading Simulator
Multi-venue execution simulator over persistent FIFO limit-order queues. Across 30-50 Monte Carlo runs, PPO reaches 5.68 bps implementation shortfall against 14.67 for TWAP.
PythonC++FastAPI
04/ 09
ML & AI
CineMatch
Personalized Recommendation Platform
Two-stage retrieve-then-rank engine. pgvector HNSW retrieval feeds a LambdaMART re-ranker at ~0.9 ms p95, for NDCG@10 of 0.814 — up 14% over popularity.
Next.jsGoPython
05/ 09
Search & Ranking
Semantic Search Service
Vector-First Retrieval with BM25 Re-Ranking
Vector-first retrieval: HNSW kNN with metadata prefilters and 5x over-fetch, then BM25 re-ranking with boosts and recency decay. CI gates relevance on MRR and NDCG@5.
JavaSpring BootElasticsearch
06/ 09
Distributed Systems
Commerce Services
Event-Driven E-Commerce Backend
SAGA-orchestrated checkout across inventory, orders, and payments. Optimistic locking cut observed deadlocks by ~40% under fault injection, with outbox events on Kafka.
JavaSpring BootKafka
BC
07/ 09
Full Stack
BC Cancer Foundation CRM
Donor Engagement Platform
Donor CRM for the BC Cancer Foundation. Weighted multi-criteria matching with explainable breakdowns, full RBAC, and an immutable audit trail.
TypeScriptNestJSReact
08/ 09
ML & AI
FaceFit AR
Browser-Based Virtual Try-On
Real-time eyewear try-on in the browser. MediaPipe Face Mesh into a Three.js overlay, with pose from classical linear algebra. Sustained 60 FPS on a mid-range laptop.
JavaScriptThree.jsMediaPipe
2
09/ 09
Mobile
QuickVerify SDK
Mobile Identity Verification
React Native SDK wrapping biometric auth (Face ID, Touch ID, BiometricPrompt) and document capture behind a single TypeScript API.
React NativeSwiftKotlin
Experience
Work history
Career arc · 2017 to now
EngineeringResearchProduct & Ops
ICBC
Northeastern MRL
Northeastern TA
Thermo Fisher (SE)
Felix Payments
USF Sales Ops
Thermo Fisher (BA)
St. Joseph's Research
20172019202120232025Now
EngineeringResearchProduct & Ops
SEP 2025 - PRESENT
Vancouver, BC
Software Engineer Intern
Insurance Corporation of British Columbia (ICBC)
MAR 2025 - JUN 2025
Vancouver, BC
AI Research Assistant
Northeastern University, Mixed Reality Lab
SEP 2024 - DEC 2024
Vancouver, BC
Graduate Teaching Assistant
Northeastern University
MAY 2024 - AUG 2024
Boston, MA
Software Engineer Intern
Thermo Fisher Scientific
JAN 2023 - AUG 2023
Vancouver, BC · Hybrid
Product Manager
Felix Payment Systems
SEP 2021 - DEC 2021
San Francisco Bay Area
Internship
Sales Operations Analyst
University of San Francisco, School of Management
MAY 2019 - DEC 2021
Toronto, ON
Full-time
Business Analyst
Thermo Fisher Scientific
MAY 2017 - APR 2019
Hamilton, ON
Full-time
Researcher
St. Joseph's Healthcare Hamilton
Awards
Honors & recognition
AwardAPR 2025
Microsoft x Qualcomm On-Device AI Hackathon
Microsoft x Qualcomm
1st Place
Real-time on-device AI navigation system for wheelchair users on Snapdragon X Elite. Fused YOLOv8 and Whisper with sub-40 ms end-to-end latency through DSP and NPU offloading.
YOLOv8WhisperSnapdragon X EliteDSP/NPU
AwardNOV 2024
Data for Good Hackathon
Telus × City of Toronto × Northeastern University
Runner-up
Built ParkSmart, a real-time urban parking optimisation PoC using Telus mobility data for lot availability predictions. Interactive heatmaps and routing algorithms applied to high-density downtown Toronto traffic.
Telus Mobility DataPythonNumPyPandasNext.js
Read contextAwardNOV 2024
Climate Resiliency Hack: Lightning Strikes
Northeastern University
3rd Place
AI-driven integration platform to help indigenous communities anticipate, prevent, and mitigate the effects of severe weather events.
Next.jsOpenAI APIFigma
Read contextAwardAUG 2024
IMC Prosperity 2 Trading Competition
IMC Trading
Rank 87 / 13,500 (Top 1% Global)
Python-based market-making and statistical arbitrage strategies. Linear regression for fair-value estimation, mean-reversion signals on residuals, and inventory-aware quoting logic that adjusted spreads based on position risk.
PythonNumPypandas
Contact
Get in touch
Best reached by email. I read everything, though replies may take a day or two.
Currently
Interested in low-latency systems, search and ML serving, and distributed backends.
Colophon · Built with Next.js 16 · Cormorant Garamond + JetBrains Mono · d3-force · Canvas 2D · Vercel · Supabase pgvector for CineMatch. All figures cited from the linked project sources. Press ⌘K to search this site.