/ 01
Roles and Responsibilities
- Design and ship LLM-powered features end-to-end with Python and FastAPI.
- Build retrieval pipelines (RAG) with vector stores and hybrid search.
- Develop agentic workflows using frameworks like LangGraph or AutoGen.
- Define evaluation harnesses to track quality, cost, and latency.
- Integrate observability and guardrails for safe production use.
/ 02
Technical Skills
- Strong Python and FastAPI background with production experience.
- Hands-on with OpenAI, Anthropic, or open-source LLMs.
- Experience with vector databases (pgvector, Pinecone, Weaviate).
- Prompt engineering, function calling, and structured output design.
- Familiarity with MLOps basics — eval, monitoring, versioning.
/ 03
You should have
- A pragmatic approach to AI — quality and cost matter as much as novelty.
- Curiosity to keep up with a fast-moving ecosystem.
- Comfort partnering with product to shape AI-native features.
- Discipline around evaluation, not just vibes-based testing.
Ready to join as a AI Engineer?
Send us your application — we read every one.