Frontier AI Engineer

Postman•Remote, WA, US, WA

3d•$300,000 - $350,000•Onsite

About The Position

Postman is building a small Frontier AI Engineering team to work directly with ambitious customers on designing, building, and bringing AI and agentic systems into production. This hands-on engineering role involves writing code, building prototypes, debugging systems, making architecture decisions, and working alongside customer engineering teams to deliver working solutions. The work spans models and inference, agents, APIs, tools, context, evaluation, security, observability, and production infrastructure. The role also brings customer learnings back into Postman. Engineers identify recurring challenges and turn them into reusable primitives, reference architectures, workflows, and product capabilities. As an early member of the team, the engineer will help define its technical bar, architecture, engineering practices, operating model, and culture. The position is based in person at one of Postman's hubs. Postman describes its work culture as inclusive, collaborative, and focused on curiosity, transparency, clear goals, and delivering excellent products.

Requirements

Strong engineering fundamentals, AI fluency, technical depth, curiosity, judgment, speed, and ownership.
Deep technical interest and a hands-on approach to building and debugging systems.
Ability to work through architecture with engineering teams as well as diagnose systems directly in code and tooling.
Understanding that production LLM systems require systems engineering, evaluation, reliability, data, APIs, and security, beyond prompt writing.
Comfort with hard, ambiguous problems and starting work without fully defined requirements.
Interest in building agents and AI systems that operate in real production environments.

Nice To Haves

Background in applied AI, agentic systems, AI infrastructure, distributed systems, developer platforms, APIs, security, ML infrastructure, inference, or model platforms.

Responsibilities

Build and ship AI systems using LLMs, agents, MCP, APIs, tool calling, RAG, vector search, structured outputs, multimodal models, and production AI workflows.
Design agentic systems that work across tools, APIs, enterprise data, and workflows while maintaining appropriate identity, permissions, policy, and execution controls.
Experiment with foundation models, model routing, inference, prompt and context engineering, and fine-tuning where appropriate; assess tradeoffs among quality, latency, cost, and reliability.
Build evaluation systems for agents and LLM applications, covering task success, tool correctness, hallucination detection, regression testing, safety, latency, and cost.
Improve production readiness through observability, tracing, guardrails, fallback strategies, rate limits, retries, caching, model gateways, and reliable operating infrastructure.
Help customers address retrieval, memory, grounding, context windows, embeddings, vector databases, enterprise data, and context delivery to models and agents.
Develop controls for secure agent actions, including authentication, authorization, secrets, API access, policy enforcement, human approval, and auditability.
Own loosely defined problems end to end, from architecture and prototyping through evaluation and production.
Prototype, integrate, debug, experiment, benchmark, and ship hands-on engineering solutions.
Work directly with customer AI teams, platform teams, developers, and engineering leaders.
Use customer challenges to inform Postman's AI platform, APIs, Gateway, identity, agent capabilities, developer experience, and product roadmap.
Identify recurring customer problems and turn them into reusable primitives, reference architectures, workflows, and platform capabilities.
Help establish the team's technical standards, architecture, engineering practices, operating model, and culture.