Frontier AI Engineer

Postman•New York, NY

3d•$300,000 - $400,000•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 collaborating closely with customer engineering teams. Work may include agent tool use, MCP integrations, retrieval-augmented generation (RAG), evaluation frameworks, routing across LLM providers, and identity and policy controls for agent actions. The role spans models and inference, agents, APIs, tools, context, evaluation, security, observability, and production infrastructure. Frontier AI Engineers bring insights from customer work back into Postman, identifying recurring engineering challenges and turning them into reusable product capabilities, primitives, reference architectures, workflows, and platform features. Engineers joining the early team will help define its technical standards, architecture, practices, operating model, and culture. The position is based in person at a Postman hub. Most listed hubs require five days per week in the office; Bangalore employees currently work three days per week and are expected to transition to five days by year-end. The reasonably estimated base salary is $300,000 to $400,000, plus a competitive equity package. Actual compensation depends on skills, qualifications, and experience.

Requirements

Strong engineering fundamentals, AI fluency, technical depth, curiosity, judgment, speed, and ownership.
Deep technical interest and a strong inclination to build hands-on.
Comfort debugging agent traces in a terminal and collaborating with engineering teams on architecture.
Understanding that production LLM systems require systems engineering, evaluation, reliability, data, APIs, and security in addition to prompt writing.
Ability to handle hard, ambiguously defined problems and begin building without needing every detail specified.
Interest in building AI and agent 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 AI systems and production workflows using LLMs, agents, MCP, APIs, tool calling, RAG, vector search, structured outputs, and multimodal models.
Design agents that work across tools, APIs, enterprise data, and workflows while applying appropriate identity, permission, policy, and execution controls.
Experiment with foundation models, model routing, inference, prompt and context engineering, and fine-tuning where appropriate; assess quality, latency, cost, and reliability tradeoffs.
Build evaluation systems for agents and LLM applications, measuring task success, tool correctness, hallucinations, regressions, safety, latency, and cost.
Improve production readiness through observability, tracing, guardrails, fallbacks, rate limits, retries, caching, model gateways, and reliable infrastructure.
Help customers solve context challenges involving retrieval, memory, grounding, context windows, embeddings, vector databases, and enterprise data.
Develop security controls for agent actions, including authentication, authorization, secrets, API access, policy enforcement, human approval, and auditability.
Own ambiguous problems end to end, from architecture and prototyping through evaluation and production deployment.
Prototype, integrate, debug, experiment, benchmark, and ship code.
Work with customer AI teams, platform teams, developers, and engineering leaders to address challenging engineering problems.
Bring customer insights into Postman's AI platform, APIs, Gateway, identity, agent capabilities, developer experience, and product roadmap.
Identify recurring customer needs and turn them into reusable primitives, reference architectures, workflows, and platform capabilities.
Help establish the technical bar, architecture, engineering practices, operating model, and culture of Frontier AI Engineering at Postman.