Harnham is a rapidly growing team seeking a Staff AI Engineer to architect, build, and scale intelligent systems for next-generation platform capabilities. This high-impact role will involve leading the design and ownership of production AI systems, establishing foundational AI architecture, and serving as a technical authority across teams.
Responsibilities:
- Lead the design and end-to-end ownership of production AI systems, including LLM pipelines, RAG architectures, embeddings, vector databases, reranking, and orchestration
- Establish foundational AI architecture and influence how intelligent systems are built, evaluated, and deployed
- Create evaluation frameworks that measure retrieval quality, reasoning accuracy, workflow performance, and system reliability
- Develop internal tooling that supports rapid experimentation without compromising safety or stability
- Serve as the technical authority across teams for AI quality, observability, safety guardrails, and operational excellence
Requirements:
- 10+ years of software engineering experience, with 3+ years focused on ML/AI systems
- Demonstrated ownership of LLM‑powered solutions in production environments
- Deep experience with RAG, embeddings, reranking, and vector stores (e.g., Pinecone, FAISS, Chroma)
- Strong proficiency in Python; familiarity with TypeScript a plus
- Ability to structure and solve ambiguous, high‑stakes technical problems using evidence‑driven decision‑making
- Excellent communication skills and comfort collaborating with cross‑functional teams
- Background in compliance, security, or other regulated industries
- Experience with Snowflake or enterprise data platforms
- Familiarity with orchestration systems such as Temporal or Airflow
- Experience with LLM evaluation platforms (e.g., Braintrust)
- Contributions to technical communities or published work