CUDA Kernels Suite

Work in Progress CUDA C++ • Nsight Systems/Compute • PyTorch

A from-scratch suite of GPU kernels (vector add, tiled matrix multiplication, reduction, softmax, and attention) built to understand GPU performance from the hardware up. Every kernel is profiled with Nsight Systems/Compute and benchmarked head-to-head against cuBLAS and PyTorch using CUDA-event timing with warmup and median-of-many-iterations methodology.

  • Hand-written CUDA kernels with standalone nvcc builds and self-tests
  • Benchmark harness plotting GFLOPS vs problem size against cuBLAS/PyTorch baselines
  • Profiling-driven optimization: memory coalescing, shared-memory tiling, occupancy analysis
  • In progress: full benchmark comparison table and per-kernel optimization writeups; next up: FlashAttention-style fused attention and KV caching

Production Lifecycle Management for LLM Classifiers

MS Thesis Python • PyTorch • HuggingFace • EvidentlyAI

An MLOps framework for keeping LLM classifiers reliable after deployment, treating the model not as a one-off artifact but as a system that must be monitored, evaluated, and retrained as the world drifts away from its training data.

  • Production monitoring and data drift detection using statistical tests
  • Active learning strategies to select the highest-value samples for relabeling
  • Incremental fine-tuning pipelines for continuous model updates

RAGstoRiches: Agentic Financial RAG System

Live Python • FastAPI • React • Qdrant • FastMCP

An agentic RAG system for financial data that lets an LLM agent combine semantic retrieval with structured SQL analysis: SQL exposed as a FastMCP tool server, Qdrant Cloud for vector search, Supabase for authentication, and Databricks-hosted Postgres.

  • Agentic tool use: SQL served to the agent as a FastMCP tool server
  • Qdrant Cloud vector database for semantic retrieval
  • FastAPI backend with a React/TypeScript frontend, hosted on Hugging Face Spaces