AI/ML Engineer: Production Agents & RAG Architect (Hybrid)

Harnham; San Francisco (CA); Hybrid; USD 315,000 - 385,000; Full time

Job summary

Harnham, a Bay Area–based data and AI solutions provider, seeks an AI/ML Engineer (All Levels) to architect end-to-end AI agents and RAG pipelines. You will shape the intelligence layer of a rapidly growing platform, making architectural decisions around model selection, fine-tuning, and evaluation while shipping directly to customers.

The role emphasizes ownership, production readiness, and collaboration with teams building AI-native data infrastructure for Fortune 500 enterprises.

Qualifications

• 4-6+ years of software engineering with meaningful AI/ML depth.
• Proven experience building and shipping AI agents in production.
• Strong Python skills with RAG, vector databases, and knowledge graphs.
• Experience with LLM APIs, prompt engineering, and production-grade outputs.
• Familiarity with AWS and Kubernetes for production AI deployment.
• Experience with data platforms such as Databricks, Snowflake, BigQuery, or Spark is a strong bonus.
• Scale or Go experience is a bonus.

Responsibilities

• Architect multi-step AI agents end-to-end, including problem decomposition and context retrieval.
• Own RAG pipelines, vector/graph retrieval systems, and knowledge representations for enterprise data.
• Build the AI layer behind the platform’s code generation capability from prompts to fine-tuning.
• Ensure production AI operates at scale with balanced latency and observability.
• Think in failure modes and evaluation strategy; own the improvement loop.

Skills

Python

AI/ML

LLM APIs

AWS

Kubernetes

RAG & vector DBs

Knowledge graphs

Go

Tools

Databricks

Snowflake

BigQuery

Spark

Job description

Harnham, a Bay Area–based data and AI solutions provider, seeks an AI/ML Engineer (All Levels) to architect end-to-end AI agents and RAG pipelines. You will shape the intelligence layer of a rapidly growing platform, making architectural decisions around model selection, fine-tuning, and evaluation while shipping directly to customers.

The role emphasizes ownership, production readiness, and collaboration with teams building AI-native data infrastructure for Fortune 500 enterprises.