GenAI Engineer — On-Site, Production-Grade AI Features

Zof AI, Inc.; San Francisco (CA); On-site; USD 140,000 - 230,000; Full time

Benefits offered by this job

MacBook Pro

Premium AI development tools

Cursor Ultra

Claude Code Ultra

OpenAI Codex Max

High-performance AI product env

Job summary

Zof AI in San Francisco, CA, is hiring a Generative AI Engineer to build product features on frontier model APIs. This is a full-time, on-site role that shapes the model-facing layer of our products, including retrieval and RAG pipelines, tool use, and context engineering.

The ideal candidate ships LLM-powered features to real users and treats quality, cost, and latency as core engineering constraints in production.

Qualifications

• Experience shipping LLM-powered features to production.
• Strong software engineering foundation.
• Working knowledge of retrieval, RAG, and agent patterns.
• Fluency with the modern model API and tooling ecosystem.
• Judgment about quality, cost, and latency trade-offs.
• Clear written and verbal communication.
• Comfort operating in a fast-moving environment.
• Evidence of building high-quality technical work.

Responsibilities

• Design and build product features on top of frontier model APIs.
• Build and tune retrieval and RAG pipelines end to end.
• Design agent planning, tool use, and multi-agent orchestration.
• Own prompt and context engineering as a disciplined, tested practice.
• Wire evals into the development loop so quality is measured, not assumed.
• Optimize the cost, quality, and latency of AI features in production.
• Collaborate with product and engineering to ship reliably and fast.
• Own model-layer systems from design through production.

Skills

LLM in production

Software engineering

Retrieval & RAG

Agent patterns

Model API tooling

Quality vs cost trade-offs

Communication

Fast-paced environment

High-quality work

Multi-agent frameworks

Tools

TypeScript

Python

Node.js

PostgreSQL

Job description

Zof AI in San Francisco, CA, is hiring a Generative AI Engineer to build product features on frontier model APIs. This is a full-time, on-site role that shapes the model-facing layer of our products, including retrieval and RAG pipelines, tool use, and context engineering.

The ideal candidate ships LLM-powered features to real users and treats quality, cost, and latency as core engineering constraints in production.