Software Engineer, Applied AI

Our client is building secure AI infrastructure that enables organizations to automate complex, high-stakes workflows where reliability, security, and trust are critical. Their platform supports agentic workflows operating across sensitive data environments, helping organizations leverage AI while maintaining appropriate controls, visibility, and governance.

We're hiring a Software Engineer to help build the production AI systems that power the company's core platform, sitting at the intersection of agentic workflows, enterprise data, and security boundaries.

This is a foundational role on the engineering team, and we're looking for someone who has shipped AI systems used by real users and has the software judgment to harden them for sensitive data and scale. This includes experience designing clear access controls, measurable quality standards, failure handling, and debuggable systems.

While this is not a research role, it does require practical ML and LLM fundamentals. You should understand enough about how models are trained, evaluated, served, and deployed to make sound engineering decisions when building AI-powered products.

What You'll Do

Build Production AI Workflows

• Build agentic workflows that operate across enterprise data and business systems, with clear controls around model access, tool usage, and human review.
• Design context and grounding systems that provide models with the right information at the right time while maintaining security and performance requirements.
• Work across backend services, APIs, asynchronous workers, data pipelines, internal tools, and product-facing applications.

Engineer Reliable LLM Systems

• Build evaluation frameworks and feedback loops for model behavior and workflow outcomes.
• Own tracing, observability, and runtime visibility across models, context, tool calls, and generated outputs.
• Debug failures using evidence from traces, tool responses, user feedback, and production logs.
• Improve quality while balancing latency, cost, reliability, and security.

Build Reusable AI Infrastructure

• Create shared primitives for context assembly, grounding, tool orchestration, and reviewable outputs.
• Build reusable platform capabilities that support multiple customer and workflow use cases.
• Partner closely with engineering and product leaders to move quickly from prototype to production.

Lead Through Ownership and Engineering Quality

• Take ownership of critical product and platform initiatives with minimal direction.
• Write clean, maintainable code and establish clear abstractions.
• Leverage AI-assisted development tools while maintaining high standards for code quality and system reliability.
• Treat LLMs as architectural components with measurable behavior, constraints, failure modes, and operational costs.

About You

You have a track record of shipping production software and have built at least one AI product or workflow used by real users, ideally in an enterprise or large-scale environment.

You have strong software engineering fundamentals and are fluent in Python and/or TypeScript. The technology stack includes modern frontend frameworks, cloud infrastructure, containerized services, data platforms, and AI tooling. Exact stack alignment is less important than technical depth and sound engineering judgment.

You are comfortable operating in ambiguous environments and taking ownership of important technical problems.

Strong Candidates May Also Have

• Shipped production LLM applications or agentic workflows.
• Built evaluation systems or feedback loops that identified meaningful regressions.
• Debugged production failures involving retrieval, grounding, tool usage, or model orchestration.
• Built systems operating over sensitive enterprise data with clearly defined security boundaries.
• Worked in environments where accuracy, reliability, and auditability are critical.
• Taken ownership of significant product or platform surface area early in their career.

Details

• Compensation: $170,000–$230,000 base salary plus equity
• Location: Hybrid (Seattle, WA)
• Visa Sponsorship: Not available at this time
• Benefits: Company-paid health coverage, including dependents
• Equity: Meaningful ownership opportunity with significant impact on the direction of the product and platform