Member of Technical Staff, AI Agent Development Lead

About the role

Postman is seeking a technical lead to design and deploy AI agents that operate within complex user environments. You will manage the full lifecycle of these systems, ensuring they are reliable, interpretable, and safe while working alongside research and product teams. In this capacity, you will define the architectural vision for agentic capabilities and translate high-level research into robust production services. You will own the end to end delivery of intelligent systems, balancing innovation with the practical constraints of scalability and user trust. The role requires you to navigate ambiguity and establish guardrails that allow teams to experiment safely. You will be responsible for translating abstract research goals into concrete product features that meet stringent reliability standards. Ultimately, you will act as the technical steward of the agent platform, ensuring that every deployment adheres to strict safety and alignment benchmarks.

Key facts

What you'll do

• Lead a cross-functional engineering team through the design and production of AI agents, defining technical milestones and delivery timelines.
• Architect agent systems using modern language models, focusing on modularity, scalability, and performance within the Postman infrastructure.
• Partner with research scientists to move innovations from theoretical concepts into production environments that meet enterprise standards.
• Build out core agent features including decision-making, autonomy, and dialogue management, ensuring they integrate seamlessly with existing platforms.
• Integrate safety and alignment protocols into the agent development lifecycle, from data collection through deployment and monitoring.
• Mentor technical staff and evaluate new frameworks or methodologies to maintain a high bar for engineering excellence and innovation.
• Coordinate with policy and product teams to ensure features meet ethical, legal, and user requirements before any public release.
• Design and implement testing strategies for agent behaviors, focusing on edge cases, failure modes, and adversarial inputs.
• Optimize system performance to handle large scale workloads while maintaining low latency and high availability for critical user flows.
• Establish observability and debugging tools specific to agent workflows, enabling rapid diagnosis of issues in production deployments.
• Drive the adoption of best practices for data handling, model versioning, and experiment tracking across the AI engineering organization.
• Explore and prototype novel agent capabilities, assessing their utility and risk profile for integration into the broader Postman ecosystem.
• Collaborate with security teams to identify and mitigate potential vulnerabilities in agent interactions and tool usage.
• Contribute to the broader technical community by documenting patterns, sharing insights, and shaping the roadmap for agentic features.

Requirements

• Proven experience leading technical teams in machine learning or AI engineering, specifically with agents or assistants in a production setting.
• Strong software engineering background with proficiency in Python, including experience with complex codebases and collaborative development workflows.
• Familiarity with ML frameworks such as JAX, PyTorch, or TensorFlow, and the ability to leverage them for building advanced neural network architectures.
• Deep knowledge of reinforcement learning, language models, and AI alignment, including practical experience with tuning and fine tuning techniques.
• Experience with cloud infrastructure and scalable system design, including containerization, orchestration, and distributed computing principles.
• Ability to communicate and collaborate across multidisciplinary groups, translating technical concepts for non specialist stakeholders.
• Demonstrated history of making sound technical decisions under uncertainty while balancing speed and safety in product development.
• Commitment to following engineering best practices, including code review, testing, and documentation standards that ensure maintainable systems.

Nice to have

• Prior work with conversational AI or large language models, including deployment and fine tuning in real world applications.
• Background in AI safety or alignment research, with a track record of contributing to frameworks or methodologies that improve system robustness.
• Experience building developer tools or APIs for AI integration, particularly those that simplify the process of connecting models to backend services.

Practical notes

Base salary ranges from $256,000 to $276,000, plus equity. Benefits include full medical coverage, flexible PTO, wellness reimbursement, a monthly lunch stipend, and a donation-matching program. Postman is an Equal Employment Opportunity and Affirmative Action Employer. Unsolicited resumes from agencies are not accepted. Employment is contingent upon completion of all required onboarding documents and verification of eligibility to work in the United States. The role requires full time presence in the San Francisco office, with no remote or hybrid arrangements available.