Staff AI Engineer

People in AI; San Francisco (CA); On-site; USD 250,000 - 300,000; Full time

Benefits offered by this job

Equity

Job summary

People in AI, based in San Francisco, is seeking a Staff AI Engineer to set the technical direction and build the systems behind AI-enabled workflows as part of a growing enterprise software platform. You will own retrieval, embeddings, and RAG pipelines, influence architecture, and lead design discussions with product leadership while delivering production-grade AI features.

This role emphasizes security, accuracy, cost, and reliability, with equity included as part of the compensation package

Qualifications

• Experience building production software with strong backend architecture.
• Proven track record deploying LLM-powered features.
• Strong Python and distributed systems skills.
• Experience with security, reliability and customer trust.
• Evidence of Staff-level ownership and leadership on complex projects.

Responsibilities

• Build customer-facing AI features within an established software platform.
• Own retrieval and context pipelines for LLM-powered systems.
• Shape AI architecture and reusable backend services.
• Define evaluation metrics, create test datasets, and build feedback loops.

Skills

Backend engineering

System design

Python

LLM features

RAG

Embeddings

Vector databases

Production software

Leadership

Job description

Compensation: $250,000–$300,000 base + equity

Employment Type: Full-time

Join a growing enterprise software company making AI a core part of how complex work gets done.

Our client is building AI-powered software that helps professional teams work through large volumes of information, automate demanding workflows, and deliver more accurate results.

With an established product and growing customer demand, the company is expanding the AI capabilities embedded throughout its platform. They're looking for a Staff AI Engineer to help set the technical direction and build the systems behind that next stage of growth.

The Opportunity

This is a hands-on Staff role spanning applied AI, backend architecture, and product engineering.

You'll own substantial technical problems, from getting the right information into a model's context to evaluating outputs and operating reliable AI features in production.

You'll have room to influence architecture, guide other engineers, and work closely with product leadership while staying deeply involved in building and shipping software.

What You'll Do

• Build customer-facing AI features: Develop intelligent assistance and automation within an established software platform.
• Own retrieval and context: Design ingestion, embedding, and retrieval pipelines that make complex information useful to LLM-powered systems.
• Shape AI architecture: Build scalable backend services and reusable infrastructure for AI capabilities.
• Establish evaluation practices: Define quality metrics, create test datasets, and build feedback loops that guide releases.
• Improve production performance: Diagnose failures and optimize accuracy, latency, reliability, and cost.
• Provide technical leadership: Lead design discussions, review important decisions, and help engineers deliver high-quality work.
• Partner across the business: Work with product, design, and domain specialists to solve meaningful customer problems.

What You'll Bring

• A strong track record of building production software, with depth in backend engineering and system design.
• Experience taking LLM-powered features from development into production.
• Strong Python skills and familiarity with asynchronous services and distributed systems.
• Practical experience with RAG, embeddings, vector databases, and LLM integrations.
• Experience measuring AI quality through evaluations, monitoring, and user feedback.
• Evidence of Staff-level ownership, including leading complex projects and influencing technical decisions.
• Strong product judgment and the ability to explain engineering trade-offs clearly.
• Comfort building systems where security, accuracy, and customer trust matter.