Senior AI Engineer

Harnham; San Francisco (CA); Sur place; USD 180 000 - 240 000; Plein temps

Résumé du poste

Harnham in San Francisco seeks an AI Product Engineer to shape how AI feels to users, blending front-end UI with real-time streaming and AI-driven back-end services. You will own end-to-end features from React/TypeScript UI to Node.js/Python backend, integrating LLM-driven workflows and agentic patterns.

You will collaborate with AI engineers, designers, and product managers to define API contracts, monitor latency and engagement, and iterate based on feedback to deliver reliable, high-quality

Qualifications

• 7+ years of software engineering experience shipping full-stack features in production, including 2+ years on AI-powered product features.
• Strong proficiency in React and TypeScript, with experience building responsive UIs that handle async, streaming, and real-time data.
• Solid Python and Node.js skills, with experience integrating APIs from LLM providers and orchestration frameworks.
• Hands-on experience with LLM APIs (OpenAI, Anthropic, etc.), prompt engineering, RAG, evals, and structured outputs in production.
• Familiarity with agent frameworks (LangGraph, LangChain, or custom runtimes) and building product surfaces on agentic workflows.
• Experience implementing streaming response patterns (SSE, WebSockets, chunked HTTP) and UIs that handle progressive or uncertain outputs.
• Strong product sense and a track record of cross-functional collaboration with AI/ML engineers, PMs, and designers.

Responsabilités

• Build AI-powered product features end-to-end, from React/TypeScript UI through Node.js/Python backend, with real-time streaming and human-in-the-loop interaction patterns
• Partner with AI Engineers to define API contracts and output schemas, translating RAG pipelines and agentic workflows into intuitive interactions
• Advocate for the user's perspective in technical decisions, surfacing where model outputs break down and iterating the product layer accordingly
• Build user-facing feedback loops that capture signal on AI output quality and feed it back to the broader AI team
• Instrument AI features with product-level observability, including latency, engagement, and drop-off, alongside full-stack integration testing
• Mentor engineers newer to AI product development and contribute to design reviews

Connaissances

React

TypeScript

Python

Node.js

LLM APIs

Prompt engineering

RAG

LangGraph

LangChain

WebSockets

Outils

LangGraph

LangChain

OpenAI API

Description du poste

We’re partnered with a high-growth, mission-driven SaaS company transforming how businesses build and maintain trust, with AI at the core of their next phase of innovation. The platform is redefining how critical enterprise workflows are automated, particularly in areas where reliability, auditability, and security are essential.

This is a high-impact role where you'll help define how AI feels to the customer, not just how it's built. You won't own backend infrastructure, instead, you'll make foundational decisions about how LLMs, agents, and RAG pipelines translate into real product experiences, working across streaming interfaces, agentic workflows, and guided automation in production.

What You'll Do

• Build AI-powered product features end-to-end, from React/TypeScript UI through Node.js/Python backend, with real-time streaming and human-in-the-loop interaction patterns
• Partner with AI Engineers to define API contracts and output schemas, translating RAG pipelines and agentic workflows into intuitive interactions
• Advocate for the user's perspective in technical decisions, surfacing where model outputs break down and iterating the product layer accordingly
• Build user-facing feedback loops that capture signal on AI output quality and feed it back to the broader AI team
• Instrument AI features with product-level observability, including latency, engagement, and drop-off, alongside full-stack integration testing
• Mentor engineers newer to AI product development and contribute to design reviews

Requirements

• 7+ years of software engineering experience with a proven track record shipping full-stack features in production, including 2+ years on AI-powered product features
• Strong proficiency in React and TypeScript, with experience building responsive UIs that handle async, streaming, and real-time data
• Solid Python and Node.js skills, with experience integrating APIs from LLM providers and orchestration frameworks
• Hands-on experience with LLM APIs (OpenAI, Anthropic, etc.), prompt engineering, RAG, evals, and structured outputs in production
• Familiarity with agent frameworks (LangGraph, LangChain, or custom runtimes) and building product surfaces on agentic workflows
• Experience implementing streaming response patterns (SSE, WebSockets, chunked HTTP) and UIs that handle progressive or uncertain outputs
• Strong product sense and a track record of cross-functional collaboration with AI/ML engineers, PMs, and designers

If you're interested in shaping how AI systems are built, evaluated, and deployed in high-trust environments, this is an opportunity to have direct influence on both technical direction and real-world impact at a fast-growing company.