AI Implementation Engineer

About the role

Design and ship AI features in production client products, RAG pipelines, LLM integrations, agents, and evaluation workflows. You will work with backend engineers and founders on engagements where reliability, cost, and measurable quality matter as much as the demo.

What you will do

• Design and implement RAG pipelines using LangChain, LlamaIndex, and vector databases
• Integrate LLM APIs (OpenAI, Anthropic, Gemini) with robust prompt engineering and fallbacks
• Build LLM observability with LangSmith or Langfuse, cost, latency, and quality tracking
• Design and implement AI agents with tool use for multi-step task automation
• Evaluate model quality with representative test datasets before production deployment
• Collaborate with product and engineering leads to scope AI features against real user needs

Requirements

• 2+ years of hands-on LLM/AI application development experience
• Strong Python skills with FastAPI or similar backend frameworks
• Production experience with LangChain, LlamaIndex, or similar orchestration frameworks
• Experience with vector databases (Pinecone, Weaviate, pgvector)
• Understanding of RAG architecture patterns and prompt engineering

Nice to have

• Experience with open-source LLMs (Llama 3, Mistral) via Ollama or HuggingFace
• ML model fine-tuning experience
• LLM evaluation framework experience (DeepEval, RAGAS)
• Data engineering background with dbt, Airflow, or similar