Production AI Systems Architect

Harnham; San Francisco (CA); On-site; USD 180,000 - 260,000; Full time

Job summary

Harnham is partnering with a high-growth, mission-driven SaaS company to redefine enterprise trust with AI at the core. You will architect AI systems, shape LLM pipelines, and drive evaluation and cost efficiency across production deployments.

You will collaborate across product, platform, and domain teams to translate complex requirements into scalable architectures and systems that emphasize reliability and auditability.

Qualifications

• 6+ years of software engineering with 3+ years in ML/AI systems.
• Proven experience deploying production LLM systems.
• Strong Python with solid CS fundamentals.

Responsibilities

• Design and own production AI systems end-to-end including LLM pipelines and orchestration layers.
• Build and scale RAG systems, embedding pipelines, and vector-based search infrastructure.
• Define evaluation frameworks for retrieval quality and system performance.
• Analyze production behavior, identify failure modes, and drive data-driven improvements.
• Make architectural decisions impacting team direction and tooling.
• Collaborate with product, platform, and domain teams to translate requirements into scalable systems.
• Lead best practices for reliable, observable, and cost-efficient AI systems.

Skills

6+ years experience

3+ years ML/AI

Production LLM systems

RAG embeddings

Vector databases

Python

Architectural decisions

Reliability/Observability

Cross-functional collaboration

Tools

Pinecone

FAISS

Chroma

Job description

Harnham is partnering with a high-growth, mission-driven SaaS company to redefine enterprise trust with AI at the core. You will architect AI systems, shape LLM pipelines, and drive evaluation and cost efficiency across production deployments.

You will collaborate across product, platform, and domain teams to translate complex requirements into scalable architectures and systems that emphasize reliability and auditability.