Senior AI Product Engineer - Real-Time Enterprise AI

Harnham; San Francisco (CA); On-site; USD 230,000 - 250,000; Full time

Job summary

Harnham is seeking a Senior AI Product Engineer to own customer-facing AI experiences in a fast-growing Bay Area team. You will translate LLM capabilities, agents, and RAG into polished, production-ready features that customers actually use.

You'll collaborate with Product, Design and AI/ML teams, bringing strong backend skills in Node.js and Python to build streaming, real-time interfaces and robust AI experiences across the stack. On-site in San Francisco.

Qualifications

• 5+ years of software engineering experience.
• 2+ years building AI-powered products in production.
• Backend experience with Node.js and/or Python.
• Hands-on experience with LLM APIs, RAG, structured outputs and prompt engineering.
• Exposure to agent frameworks such as LangGraph, LangChain or custom agent runtimes.
• Experience building streaming or real-time user experiences.
• Strong product instincts and collaboration with Product, Design and AI/ML teams.

Responsibilities

• Own customer-facing AI experiences end-to-end.
• Turn LLMs, agents and RAG capabilities into polished, production-ready features.
• Collaborate with Product, Design and AI/ML teams.
• Deliver real-time AI interfaces using streaming technologies.
• Shape QA signals and feedback loops.

Skills

5+ years software engineering

2+ years AI-powered products

Backend Node.js

Backend Python

LLM APIs prompt engineering

Streaming real-time interfaces

Product instincts

Tools

Node.js

Python

LLM APIs

LangChain

RAG

Job description

Harnham is seeking a Senior AI Product Engineer to own customer-facing AI experiences in a fast-growing Bay Area team. You will translate LLM capabilities, agents, and RAG into polished, production-ready features that customers actually use.

You'll collaborate with Product, Design and AI/ML teams, bringing strong backend skills in Node.js and Python to build streaming, real-time interfaces and robust AI experiences across the stack. On-site in San Francisco.