MSCS @ Northeastern Β· Former Research Engineer @ NEU Human-centered AI Lab Β· Tech Member of GetPitchin.com
- LLM Alignment & Fine-tuning β SFT, RLHF, DPO, reward modeling, and evaluation pipelines
- Reinforcement Learning β Policy optimization, value-based methods, multi-agent systems
- AI Agent Engineering β Full-stack TypeScript agents with tool-use, MCP, and orchestration
- ML Infrastructure β Training pipelines, model serving, distributed systems on AWS
ML / AI
Full-Stack & Agents
Infra & DevOps
π Writings on Medium
- Rust Ownership Intuition: Manage Data like Properties!
- Why Adopt Pin/Unpin Over Relative Pointers?
- I Tried Four Smarter Ways to Select Positions in GCG. They All Made It Worse β and Hereβs Why Thatβs Interesting
- ......