AI Engineer building across applications, agents, LLM systems, and infrastructure.
AI Engineering
RAG · GraphRAG · Knowledge Systems · Multimodal · AI APIs
Harnesses · Tool Use · Context Engineering · Memory · Agent Loops · Evals
Retrieval · Reranking · Structured Generation · Routing · Guardrails · Evaluation
Inference · vLLM · SGLang · CUDA · Observability · Distributed Systems
Selected Work
infercap
LLM inference engineering toolkit for preflight checks, serving configuration, verification, benchmarking, telemetry, and capacity analysis.
vLLM · Benchmarking · Telemetry · Capacity Analysis
Toolbox
AI Systems & Frameworks
Applications → Agents → LLMs → Systems