Work

experience, research, projects, and open source

HomeEasy Jan 2026 – Present
AI/ML and Automations Lead Engineering Intern

Architecting agent-based AI system for real-time client interaction analysis using Mistral 7B and OpenAI/Gemini APIs. Built end-to-end business intelligence platform with real-time KPI tracking and LLM-powered conversational analytics.

Mailwave Jun 2025 – Dec 2025
AI/ML Engineering Intern

Productionized voice and audio ML pipelines achieving sub-200ms end-to-end latency. Owned core voice interaction stack including control logic, prompt routing, and eval-driven iteration loops.

Independent Research

Investigated whether implicit neural representations (SIRENs) can replace KV cache memory reads with compute during LLM inference. Ran 280 SIREN fits across 7 architectures on Llama 3.1-8B. Found keys have learnable positional structure from RoPE (0.91 CosSim) but values don't (0.67). SVD dominates at every compression ratio with zero training. The hypothesis was creative but wrong; the contribution is the structural characterization of the K/V asymmetry.

PythonPyTorchCUDASIREN
Virtual AI Research Lab: Multi-Agent Scientific Reasoning Oct 2025 – Present
Lead Researcher and Systems Developer

Designing hierarchical multi-agent framework modeling virtual research institute with independent labs exploring competing hypotheses.

ConjectureBench: Semantic Alignment for Formal Mathematics Dec 2025 – Present
Research Collaborator (w/ DeepMind Researcher)

Designing benchmark to detect "Silent Failure" in AI systems producing semantically incorrect but syntactically valid conjectures.

Cottus Runtime

C++/CUDA LLM inference engine for Llama with PagedAttention (40% memory reduction) and cuBLAS kernels (2.3x speedup). Custom CUDA kernels for Multi-Head Attention, RoPE embeddings, and GEMM operations.

C++20CUDAcuBLASPyBind11

StoneDB-Engine

A modular, ACID-compliant embedded database written in C++ with two-phase locking, WAL, deadlock detection, and LRU page cache.

C++17ACIDConcurrency

Helix

A semantic vector engine for scalable similarity search built in C++20.

C++20Vector Search
OpenAI Agents SDK Oct 2025 – Present
Core Contributor

Worked on core SDK features; added compaction via responses.compact API, fixed PCM audio duration calculation and VAD truncation handling, improved strict schema compatibility, and added extensible data payloads to lifecycle hooks.

Google DeepMind Formal Conjectures Dec 2025 – Present
Contributor

Formalizing Erdős Problems in Lean 4: Ramsey size linearity (Q3, K33, H5), doubly exponential lower bounds for hypergraph Ramsey numbers, asymptotic growth of hypergraph Ramsey numbers, logarithmic density of size-dependent congruences, and the Lebesgue-Nagell equation conjecture.