Frontier AI Engineer

Overview

Hands-on Frontier AI Engineer role on a small team that works directly with Postman's most ambitious customers to design, build and bring real AI and agentic systems into production, then turns the repeated lessons into product capabilities.

What you'll do

• Build real AI systems working with LLMs, agents, MCP, APIs, tool calling, RAG, vector search, structured outputs, multimodal models and production AI workflows.
• Design agentic systems that reason across tools, APIs, enterprise data and workflows while maintaining the right controls around identity, permissions, policy and execution.
• Work across the model layer, including foundation models, model routing, inference, prompt and context engineering, fine tuning where it makes sense, and the tradeoffs between quality, latency, cost and reliability.
• Make AI measurable by building evaluation systems for agents and LLM applications, covering task success, tool correctness, hallucination detection, regression testing, safety, latency and cost.
• Make AI production ready through observability, tracing, guardrails, fallback strategies, rate limits, retries, caching, model gateways and the infrastructure needed to operate AI systems reliably at scale.
• Help customers reason about retrieval, memory, grounding, context windows, embeddings, vector databases, enterprise data, and how the right context reaches the right model or agent at the right time.
• Secure agent actions through authentication, authorization, secrets, API access, policy enforcement, human approval, auditability and the controls required when AI systems can take actions.
• Own problems end to end, taking an ill-defined problem from architecture to prototype to evaluation to production.
• Stay close to the code by prototyping, integrating, debugging, experimenting, benchmarking and shipping.
• Spend time with AI teams, platform teams, developers and engineering leaders at customer engineering teams.
• Feed field problems back into Postman's AI platform, APIs, Gateway, identity, agent capabilities, developer experience and product roadmap.
• Turn repeated customer patterns into reusable primitives, reference architectures, workflows and platform capabilities.
• Help define the technical bar, architecture, engineering practices, operating model and culture of the Frontier AI Engineering team.

What you'll need

• Deep technical background and a love of building.
• Ability to debug an agent trace and to work through architecture with another engineering team.
• Understanding that LLM work is systems engineering, covering evaluation, reliability, data, APIs and security to make probabilistic systems behave predictably in production.
• Strong engineering fundamentals, AI fluency, technical depth, curiosity, judgment, speed and ownership.
• Background in applied AI, agentic systems, AI infrastructure, distributed systems, developer platforms, APIs, security, ML infrastructure, inference or model platforms.
• Comfort taking on problems that are not fully defined before building starts.

Details

• Location: Remote, WA, US.
• Base salary reasonably estimated at $300,000 to $350,000, plus a competitive equity package; actual compensation depends on skills, qualifications and experience.
• Postman offers pay-on-performance, a flexible schedule, comprehensive benefits, flexible PTO and a monthly lunch stipend.