Staff AI Engineer - Architect of Production LLM Systems

Harnham; San Francisco (CA); On-site; USD 180,000 - 240,000; Full time

Job summary

Harnham is seeking a seasoned software engineer to shape how AI is built, evaluated, and deployed in a high-growth SaaS environment. You will design and own production AI systems end-to-end, including LLM pipelines, retrieval systems, and orchestration layers, driving reliability, scalability, and cost efficiency.

You will collaborate with product, platform, and domain teams to translate complex requirements into scalable architectures, set evaluation frameworks, and guide long-term technical

Qualifications

• 10+ years of software engineering experience, with 3+ years on ML or AI systems.
• Proven experience owning and deploying production LLM systems.
• Strong Python skills and solid software engineering fundamentals.
• Experience with architectural decision-making at team or org level.
• Excellent cross-functional collaboration and communication.

Responsibilities

• Design and own production AI systems end-to-end, including LLM pipelines, retrieval systems, and orchestration layers.
• Build and scale RAG systems, reranking pipelines, and vector-based search infrastructure.
• Define evaluation frameworks to measure retrieval quality, reasoning accuracy, and system performance.
• Analyze production behavior, identify failure modes, and drive improvements based on data.
• Make key architectural decisions across model infrastructure, tooling, and workflows.
• Partner closely with product, platform, and domain teams to translate complex requirements into scalable systems.
• Lead best practices for building reliable, observable, and cost-efficient AI systems.

Skills

AI systems design

LLM pipelines

RAG and embeddings

Python

Production systems

Tools

Pinecone

FAISS

Chroma

Job description

Harnham is seeking a seasoned software engineer to shape how AI is built, evaluated, and deployed in a high-growth SaaS environment. You will design and own production AI systems end-to-end, including LLM pipelines, retrieval systems, and orchestration layers, driving reliability, scalability, and cost efficiency.

You will collaborate with product, platform, and domain teams to translate complex requirements into scalable architectures, set evaluation frameworks, and guide long-term technical