AI Engineering
Agentic systems, RAG, evals, and on-prem deployments. We integrate frontier models when they're the right call and run open-weights on your own metal when they aren't.
- Claude Agent SDK / MCP servers
- Retrieval with pgvector / Qdrant
- Evals: Inspect, Braintrust, Promptfoo
- On-prem: vLLM, Ollama, llama.cpp
- Fine-tuning: LoRA, QLoRA, DPO
- Voice agents & computer-use