AI Engineer

About the role

We are looking for an AI Engineer to design, build, and ship production‑grade AI features for our enterprise products. This role focuses on delivering reliable, user‑facing systems rather than research, covering everything from problem framing to deployment and continuous improvement.

Key responsibilities

• Develop and maintain Retrieval‑Augmented Generation (RAG) pipelines, agentic workflows, and LLM‑powered services using Python, FastAPI, and vector stores such as Pinecone, Chroma, or pgvector.
• Design prompt strategies, evaluation harnesses, and guardrails to ensure production reliability and measurable quality.
• Integrate LLM APIs (OpenAI, Anthropic, Hugging Face, or local inference) into existing product surfaces, selecting models based on cost, latency, and accuracy.
• Ship features behind feature flags, instrument them, and iterate based on user signals and evaluation results.
• Collaborate with backend, frontend, and product teams to define scope, build data pipelines, and ensure seamless integration.
• Document implementations thoroughly for future engineers.

Required profile

• 3–5 years of professional software engineering experience, with at least one year hands‑on with LLMs or applied ML in production.
• Strong Python skills and experience with FastAPI or a comparable async framework.
• Practical experience with at least one agentic framework (LangChain, LlamaIndex, LangGraph, CrewAI, or a custom solution).
• Working knowledge of vector databases, embedding models, chunking strategies, and retrieval failure modes.
• Proficient SQL skills; PostgreSQL preferred.
• Familiarity with Docker, Git, and a major cloud platform (AWS, GCP, or Azure).

Required skills

• Python
• FastAPI
• Async programming
• LangChain / LlamaIndex / LangGraph / CrewAI
• Vector stores (Pinecone, Chroma, pgvector)
• Embedding models & retrieval techniques
• SQL / PostgreSQL
• Docker
• Git
• AWS, GCP or Azure
• OpenAI, Anthropic, Hugging Face APIs