AI Architect: Enterprise Agents & Data Infra

Harnham; San Francisco (CA); On-site; USD 170,000 - 240,000; Full time

Job summary

Harnham is seeking an experienced AI/ML software engineer to own the intelligence layer of our platform. You will architect multi-step AI agents, design RAG pipelines, and oversee production-grade deployment choices that impact enterprise customers.

The role emphasizes building scalable AI systems, fine-tuning models, prompt engineering, and ensuring robust evaluation. You’ll collaborate with data and product teams to ship high-impact features at scale.

Qualifications

• 4–6+ years of software engineering with meaningful AI/ML depth.
• Proven experience building and shipping AI agents in production.
• Strong Python skills and hands-on experience with RAG, vector databases, and knowledge graphs.
• Experience with LLM APIs, prompt engineering, fine-tuning, and producing structured outputs in production.
• Familiarity with AWS and Kubernetes for production AI deployment.

Responsibilities

• Architect multi-step AI agents end-to-end, including problem decomposition, context retrieval, error handling and output quality.
• Own RAG pipelines, vector databases and knowledge representations for enterprise data.
• Build the AI layer behind the platform's core code generation, from prompts to fine-tuning and validation.
• Ensure production AI works at scale, balancing latency, throughput and observability.
• Think in failure modes, define evaluation strategies, and drive the improvement loop.

Skills

AI/ML depth

AI agents in prod

Python

LLM APIs

Prompt engineering

Education

Bachelor's degree in CS or related field

Tools

RAG pipelines

Vector databases

Knowledge graphs

Databricks

Snowflake

BigQuery

Spark

Go

Job description

Harnham is seeking an experienced AI/ML software engineer to own the intelligence layer of our platform. You will architect multi-step AI agents, design RAG pipelines, and oversee production-grade deployment choices that impact enterprise customers.

The role emphasizes building scalable AI systems, fine-tuning models, prompt engineering, and ensuring robust evaluation. You’ll collaborate with data and product teams to ship high-impact features at scale.