Applied AI Engineer

Zof AI; San Francisco, Northern (CA, KY); Hybrid; USD 140,000 - 190,000; Full time

Job summary

Zof AI in San Francisco, CA is seeking an Applied AI Engineer to build product features on top of frontier model APIs. This role owns the model-facing layer of our products, including retrieval and RAG pipelines, agent planning and orchestration, multi-agent frameworks, and the context engineering that makes AI systems reliable in production.

You have shipped LLM-powered features to real users and treat quality, cost, and latency as engineering constraints.

Qualifications

• Shipping LLM-powered features to production.
• Strong software engineering foundation.
• Knowledge of retrieval, RAG, and agent patterns.
• Fluency with modern model APIs.
• Ability to balance quality, cost, and latency.

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 features

Software engineering

Model APIs

Retrieval & RAG

Tools

TypeScript

Python

Node.js

Postgres

Job description

Zof AI is seeking an Applied AI Engineer to build product features on top of frontier model APIs. This role owns the model-facing layer of our products: retrieval and RAG pipelines, agent planning and orchestration, multi-agent frameworks, and the context engineering that makes AI systems reliable in production. If you have worked as a GenAI Engineer, LLM Engineer, RAG Engineer, or Algorithm Engineer, this is that discipline at Zof AI. The ideal candidate has shipped LLM-powered features to real users and treats quality, cost, and latency as engineering constraints, not afterthoughts.

Engineering · Mid to Senior · Full-time · On-site · San Francisco, CA

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.

Requirements

• 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.

Nice to have

• Experience with multi-agent frameworks or agent orchestration systems.
• Experience building or using eval harnesses.
• Experience with TypeScript, Python, Node.js, Postgres, or similar technologies.
• Experience with fine-tuning or model adaptation.

Deep, hands-on experience building production features on top of LLM APIs is required