RésuméDownload PDF

• Bachelor of Science in Electrical & Computer Engineering, GPA 3.75 / 4.00.
• Expected graduation: December 2028.

• Developing PrivateMind, Options IT's secure and private AI infrastructure for enterprise environments.
• Deploying distributed systems to serve open-weight models across NVIDIA B300/B200 GPU infrastructure.
• Leveraging data center colocation across major financial hubs New York and London to deliver low-latency compute while enforcing hardware-isolated, zero-trust boundaries for T1 financial institutions.

• Led 8-person engineering team at Cornell in building an ESG risk monitoring platform for Investcorp's investment portfolio business, driving engineering efforts while coordinating with stakeholders worldwide (Feb. 2026 – May 2026).
• Implemented vendor due diligence agentic pipeline with fintech company QuickFi (Sept. 2025 – Dec. 2025).

• Collaborated with a PhD researcher in Cornell NLP Group on LLM safety alignment.
• Engineered pipeline to evaluate safety-alignment across frontier models in adversarial prompt settings.
• Worked with B200-class GPUs to run LLMs locally, using tools like vLLM and SGLang.

• Collaborated with Dr. Amit Lakhanpal to analyze immunological datasets and extract clinical insights.
• Generated protein embeddings using Meta's ESM model to support rheumatoid arthritis treatment research.

Agentic penetration testing platform that turns vulnerability findings into ready-to-merge GitHub PRs. / Best Developer Tool — Cornell AI Hackathon 2026

• Orchestrates security agents using Mastra and OpenRouter, with isolated execution via Blaxel Sandboxes
• Slackbot and Datadog middleware for triggering scans and ingesting logs to surface findings
• Converts raw scan output into reviewable, mergeable remediation PRs

Training-free jailbreak in which an uncensored model steers the target's chain-of-thought. / Publication · Source

• Achieves near-universal compliance across open-weight models (DeepSeek, Kimi, GLM, Qwen)
• Iterative prompt injection and LLM-as-judge pipelines to streamline evaluation
• Evaluated 15 frontier models across 800 WMDP-derived biosecurity and chemical security requests

Moderated, unbiased debate platform built on organized layouts and AI summaries. / Source

• Fact-checking pipelines with web data normalization, preventing hallucinations in consensus
• LLM-driven consensus tracker built on the Anthropic API, Supabase, and Vercel/Railway

PyTorch interface with automatic optimization and profiling, built to cut boilerplate in ML research. / Source

• Pluggable architecture with configurable multi-accelerator support
• Automatic data splitting and built-in profiling hooks

• Built Dispatch, an agentic penetration testing platform automating vulnerability detection and remediation
• Developed integrations with Datadog, Slack, and Linear for seamless integration with developer workflows