Senior/Staff Software Engineer, AI

People in AI; San Francisco (CA); Hybrid; USD 140,000 - 200,000; Full time

Job summary

People in AI is seeking experienced software engineers who have moved deeply into applied AI. You will design and build production AI systems used directly within the company’s core product, owning them end-to-end from architecture through deployment and monitoring.

You will build infrastructure for LLM agents, retrieval, RAG, evaluations, observability, and workflow orchestration, while collaborating with product and design teams to create reliable software for complex professional workflows.

Qualifications

• Strong software engineering experience with backend/platform/infrastructure focus.
• Track record shipping technically difficult systems into production.
• Recent experience building production AI systems involving LLMs, agents, retrieval, or evaluation.

Responsibilities

• Design and build production AI systems used within the core product.
• Own systems end-to-end from architecture to deployment and monitoring.
• Build infrastructure for LLM agents, retrieval, RAG, evaluations, observability, and workflow orchestration.
• Develop evaluation and feedback systems for AI features.
• Make architectural decisions around models, retrieval, orchestration, and tradeoffs.

Skills

Backend engineering

Distributed systems

Production AI systems

LLMs

Agent systems

RAG

Tools

Python

Go

Job description

Location: San Francisco, hybrid

Employment Type: Full-time

We’re working with a fast-growing, well-funded B2B SaaS company building AI-native software for complex, high-value professional workflows.

AI is becoming a core part of the product, and the engineering team is building the software and platform capabilities needed to make increasingly capable AI systems reliable in production.

The team is looking for experienced software engineers who have moved deeply into applied AI. The strongest candidates will have a strong foundation in backend or platform engineering and have since taken meaningful ownership of production LLM, agent, retrieval, or evaluation systems.

What You’ll Do

• Design and build production AI systems used directly within the company’s core product
• Own systems end-to-end, from architecture and implementation through deployment, monitoring, and iteration
• Build infrastructure for LLM agents, retrieval, RAG, evaluations, observability, and workflow orchestration
• Build evaluation and feedback systems
• Make architectural decisions around models, retrieval approaches, orchestration patterns, and system tradeoffs
• Work closely with product, design, and domain experts to turn ambiguous problems into reliable software

What We’re Looking For

• Strong software engineering experience, ideally in backend, platform, infrastructure, or distributed systems
• A track record of owning technically difficult systems and shipping them into production
• Recent experience building production systems involving LLMs, AI agents, RAG/retrieval, tool calling, or evaluation
• Experience in a high-growth Seed–Series C product company is strongly preferred
• Comfortable operating in a high-ownership environment where engineers are expected to solve ambiguous problems independently

Why Join?

You’ll join at a point where the company already has strong funding, real customers, and an established product, while AI is becoming increasingly central to the platform.

Rather than working on isolated AI experiments, you’ll have significant ownership over the systems that determine whether AI actually works reliably for customers: orchestration, retrieval, evaluation, observability, backend architecture, and production reliability.