AI Architect

Navan • San Francisco, CA

22h

About The Position

The AI Architect will set the technical direction for how the company designs, evaluates, integrates, and operates AI systems that improve important human workflows. This strategic, hands-on role establishes reusable architecture and evaluation practices, guides cross-functional teams, and prototypes or validates key patterns. The AI Architect partners with product and engineering leaders to turn high-value opportunities into systems that can be measured and operated in production.

The role defines AI reference architectures and design principles, balancing quality, autonomy, reliability, latency, cost, and complexity. It builds evaluation practices, guides production readiness, creates reusable patterns and implementation guidance, and connects architecture to measurable workflow outcomes. The AI Architect also evaluates evolving models, agent runtimes, orchestration approaches, and evaluation tools, recommending adoption based on evidence.

Requirements

• At least 8 years of experience in backend software development.
• At least 3 years of experience in AI architecture with demonstrated organization-wide impact.
• Strong experience designing and delivering production software systems, including substantial work on AI/ML-powered products or services.
• A track record of setting technical direction across teams and influencing decisions through evidence and collaboration.
• Practical understanding of LLM applications, including retrieval and context construction, tool use, agent patterns, model selection, and failure handling.
• Experience defining quality expectations and building evaluations for AI behavior, and connecting offline evaluations to production outcomes.
• Sound judgment about when AI is appropriate and when a simpler deterministic approach is better.
• Experience with production concerns such as observability, privacy and security, reliability, cost, latency, and safe human escalation.
• Clear communication across engineering, product, and executive audiences.
• A builder’s mindset and comfort prototyping and reviewing implementation.

Nice To Haves

• Experience establishing shared AI platforms, service patterns, or architecture standards across multiple teams.
• Experience creating evaluation datasets, test harnesses, regression suites, or quality dashboards for LLM or agent systems.
• Experience operating AI products with measurable user or business outcomes.
• Experience working with cloud AI platforms, model APIs, agent frameworks, tracing/evaluation tools, and data platforms.

Responsibilities

• Define AI reference architectures and design principles for AI services, agents, model integrations, data and context flows, tools, and human review.
• Make trade-offs among quality, autonomy, reliability, latency, cost, and complexity.
• Help teams define expected AI behavior and success measures; design representative datasets and evaluation methods; write and maintain evaluations; establish regression checks and quality thresholds; and use results to prioritize improvements.
• Shape shared production practices for tracing and observability, versioning, monitoring, incident response, privacy, security, and AI-system lifecycle management.
• Create reusable patterns, reference implementations, and practical guidance to help teams ship AI systems.
• Coach engineers through architecture reviews and help teams move valuable work from prototype to production.
• Partner with product, operations, and domain teams to identify workflow needs and measure AI’s effects on completion, quality, time, or other agreed outcomes.
• Prototype high-risk or foundational designs, review critical implementations, and refine architecture using production evidence.
• Evaluate models, agent runtimes, orchestration approaches, and evaluation tooling against requirements, and recommend adoption based on evidence.

What This Job Offers

• Job Type: Full-time
• Career Level: Senior
• Education Level: No Education Listed