AI Engineer | San Francisco | $250k + equity

We’re working with a well-funded infrastructure startup building what many believe is a missing layer of the modern AI software stack: the context layer for engineering teams and AI coding agents.

This company is solving that problem by building a continuously updated, deterministic graph of an organization’s entire engineering environment. The graph acts as operational memory for both humans and AI agents, enabling safer deployments, better architectural decisions, lower production risk, and faster development.

The Role

We’re looking for an AI Engineer to help build the intelligence layer that makes this system useful to both engineers and AI agents.

You’ll work at the intersection of AI, software infrastructure, developer tooling, and knowledge representation, building systems that can understand complex engineering environments and provide reliable, actionable context.

This is an opportunity to work on a foundational problem in the next generation of AI-powered software development, with significant ownership over both the technical direction and the product.

Responsibilities:

• Build AI-powered systems that understand and reason over complex engineering environments.
• Develop intelligent workflows that combine structured data, unstructured information, code, infrastructure, and operational context.
• Work with LLMs, agents, retrieval systems, and knowledge representations to make engineering context accessible to both humans and AI.
• Design and implement systems for extracting, organizing, and continuously updating knowledge from engineering environments.
• Improve the accuracy, reliability, and determinism of AI-generated context and recommendations.
• Build integrations across code repositories, infrastructure, developer tools, documentation, communication platforms, and other engineering systems.
• Develop evaluation frameworks to measure the quality and reliability of AI systems.
• Work closely with product and engineering teams to turn ambiguous problems into scalable technical solutions.
• Help shape the architecture and technical direction of an early-stage product.

Qualifications:

• Strong software engineering fundamentals and experience building production systems.
• Experience building applications or infrastructure involving LLMs, AI agents, RAG, knowledge graphs, or other AI/ML systems.
• Strong Python and/or TypeScript experience; experience with other modern backend languages is a plus.
• Experience working with APIs, distributed systems, databases, and cloud infrastructure.
• A strong understanding of the limitations of LLM-based systems and how to build reliable systems around them.
• Experience taking AI systems from prototype through production.
• Comfort operating in an early-stage environment where you’ll have significant ownership and autonomy.
• Strong product instincts and an interest in solving difficult problems for software engineers.
• Must have unrestricted legal authorization to work in the United States; sponsorship is not available for this position.
• Must be able to do 5 days a week in San Francisco

Why Join?

You’ll be joining a well-funded team tackling a fundamental problem created by the rapid evolution of AI-powered software development.

As coding agents become increasingly capable of writing and modifying production code, understanding the environment in which that code operates becomes just as important as generating the code itself.

You’ll have the opportunity to help define this emerging category and build infrastructure that could become a critical part of how both engineers and AI agents understand, operate, and change complex software systems.