Technical Skills
Hugging Face
PyTorch
Python
Pinecone / Vector DB
FastAPI
AWS
DockerHugging FacePyTorchPythonPinecone / Vector DBFastAPIAWSDockerFine-tuning transformers, building multi-agent pipelines, and shipping production RAG systems. From LoRA adapters to agentic reasoning chains, I build LLM systems that actually work in the real world.
I specialize in building production-grade LLM applications, from fine-tuning large language models to architecting complex multi-agent systems. My work spans the entire GenAI stack: prompt engineering, RAG pipelines, vector databases, and high-performance inference optimization.
Published researcher with work at IEEE ICC 2026 on LLM-enabled path planning. I've achieved 12.3× throughput improvements through vLLM optimization.
Hugging FacePyTorchPythonPinecone / Vector DBFastAPIAWSDockerHugging FacePyTorchPythonPinecone / Vector DBFastAPIAWSDockerClick to filter by category
Loading projects...
Graduate Research Assistant
Jun 2025 - Present
CTMap project (IEEE ICC 2026) - LLM-enabled path planning. Fine-tuning LLMs for network prediction.
Machine Learning Engineer Intern
Dec 2025 - Present
Integrating GenAI capabilities into healthcare applications. Building conversational AI features.
UC Berkeley EECS • Jul 2025
Oracle Cloud • Jun 2024 - Jun 2026
Fine-tuning, RAG, agents, or clinical LLM deployment. Let's build something that works.