Engineering
AI Engineer. Builds production LLM applications, from retrieval and prompting to evaluation and deployment.
Profile
- Area
- Engineering
- Skills
- Python, Retrieval-augmented generation (RAG), Prompt and context engineering, LLM evaluation, API design, Embeddings and vector search, Model fine-tuning
- Technologies
- OpenAI, Anthropic Claude, Google Gemini, LangChain, LlamaIndex, pgvector, Pinecone, FastAPI, Docker, AWS Bedrock
What they do
- Design and ship LLM-powered features
- Build RAG pipelines over company data
- Evaluate and harden model outputs (evals, guardrails)
- Integrate models via APIs into existing products
- Optimize cost, latency and quality in production
- Fine-tune or adapt models when prompting is not enough