Staff AI Engineer

As a Staff AI Engineer, you will play a key role in shaping and delivering high-impact AI initiatives, building production-ready solutions that directly improve customer experiences. You will provide technical leadership across engineering teams, influence major architectural decisions, and help define the future of the organization's AI capabilities. Working within a collaborative, cross-functional environment, you will lead projects from initial design through production deployment. You will also strengthen the shared AI platform, establishing robust evaluation frameworks, quality standards, and scalable infrastructure. This is an opportunity to combine hands-on engineering with strategic influence, building reliable AI systems that deliver measurable value to real users.

• Lead the technical design, development, and delivery of major AI initiatives, including AI-powered assistants, contextual data systems, and generative AI features.

• Contribute directly to production AI systems from the outset, identifying technical opportunities and delivering improvements to existing architecture and workflows.

• Drive early improvements in AI quality, reliability, and performance by addressing known failure points, strengthening evaluation coverage, and implementing measurable enhancements.

• Take ownership of major AI projects from architecture and technical planning through cross-functional collaboration, deployment, and ongoing optimization.

• Define and influence architectural decisions across engineering teams, with particular responsibility for AI architecture and shared platform infrastructure.

• Establish scalable AI quality frameworks, including automated evaluations, regression testing, guardrails, agent tracing, human feedback mechanisms, and production monitoring.

• Design and implement reliable AI agents and tool integrations, balancing deterministic code and LLM capabilities while addressing security, latency, reliability, and cost.

• Drive broader engineering initiatives that improve development quality and velocity, such as AI evaluation standards, agentic software development practices, code review processes, and technical documentation.

• Collaborate closely with Product, Design, QA, Operations, and engineering stakeholders to translate business needs into effective technical solutions.

• Promote engineering excellence through technical mentorship, knowledge sharing, clear architectural standards, and a culture of continuous improvement.

• Extensive experience in software engineering at Staff Engineer or equivalent level, with a proven ability to lead complex, ambiguous initiatives as a hands-on individual contributor.

• Demonstrated experience designing, building, and deploying production-grade LLM applications, AI agents, or generative AI features used by real customers.

• Strong technical leadership skills, including the ability to influence architectural decisions across teams, establish engineering standards, and drive initiatives from proposal through implementation.

• Proven experience building and maintaining AI evaluation frameworks that combine automated testing, agent traces, human feedback, and production monitoring to measure quality and prevent regressions.

• Strong understanding of AI agent architecture, tool design, and orchestration, including the ability to determine when deterministic logic is preferable to LLM-based solutions.

• Experience designing secure and reliable tool boundaries, human-in-the-loop workflows, and systems that balance performance, latency, security, and operational costs.

• Sound judgment in build-versus-buy decisions, model selection, and AI provider integrations.

• Strong backend and platform engineering expertise, particularly with Python and Django, PostgreSQL, Redis, asynchronous workers, and REST or GraphQL APIs.

• Ability to design scalable shared AI infrastructure with well-defined interfaces, efficient caching strategies, and robust tenant isolation.

• Excellent problem-solving, communication, and collaboration skills, with the ability to work effectively across Product, Design, QA, and engineering teams.

• A pragmatic, measurement-driven approach to AI development, prioritizing evidence, evaluation, and reliability over simply changing models or rewriting prompts.