Agent Platform Engineer

Global Placement Firm • New York, NY

14d • Onsite

About The Position

Global Placement Firm is conducting a confidential search for a Senior Software Engineer specializing in AI agent infrastructure and backend systems to join a rapidly growing healthcare AI technology startup in New York City. This is an on-site engineering role for an experienced software engineer with expertise in TypeScript backend development, production-grade infrastructure, distributed systems, and AI agent architecture. The posting seeks a candidate with at least four years of professional software engineering experience who is interested in building reliable, scalable systems that enable AI agents to automate healthcare workflows.

The engineer will design, build, and scale backend systems for autonomous AI agents that operate across healthcare environments and tools, including electronic medical records, healthcare portals, browser and desktop applications, documents, and fax-based workflows. The role includes ownership of agent architecture, backend infrastructure, workflow orchestration, evaluation systems, and platform reliability. The engineer will collaborate with engineering leadership, forward-deployed engineers, and product teams to turn implementation challenges into reusable platform capabilities.

The position is based on-site in New York City and offers a base salary of $150,000–$230,000 annually plus competitive equity. Employment is full-time. The search is being presented by Global Placement Firm on behalf of a confidential healthcare AI technology client.

Requirements

• At least 4 years of professional software engineering experience, with an emphasis on backend engineering and infrastructure development.
• Deep proficiency in TypeScript and Node.js.
• Demonstrated experience designing, building, and maintaining production-grade backend systems.
• Strong understanding of distributed systems, asynchronous processing, and scalable infrastructure.
• Experience developing APIs, background jobs, domain services, and event-driven applications.
• Experience with relational databases such as PostgreSQL.
• Strong knowledge of system reliability, fault tolerance, observability, and performance optimization.
• Experience designing clean software abstractions and reusable platform components.
• Familiarity with AI agents, LLM-based applications, or modern AI infrastructure.
• Experience in fast-moving engineering environments with significant individual ownership.
• Strong debugging, problem-solving, and technical communication skills.
• Ability to collaborate with engineers across infrastructure, product, and customer-facing teams.
• Comfort working on-site in New York City and collaborating closely with a rapidly evolving engineering team.

Nice To Haves

• Hands-on experience developing computer-use agents or autonomous AI systems.
• Experience with browser automation frameworks such as Playwright.
• Experience with workflow orchestration technologies such as Temporal.
• Familiarity with Prisma ORM and modern TypeScript backend architectures.
• Experience with Google Cloud Platform (GCP).
• Experience with Docker, Pulumi, and infrastructure-as-code technologies.
• Experience designing evaluation and observability systems for AI agents.
• Experience integrating LLMs into production applications.
• Familiarity with agent planning, memory, tool use, execution, and recovery systems.
• Experience building automation across multiple applications or external systems.
• Experience at an early-stage or rapidly scaling technology startup.
• Healthcare technology or workflow automation experience.
• Familiarity with AI-assisted engineering tools such as Cursor and Claude Code.

Responsibilities

• Design, build, and maintain core infrastructure powering autonomous AI agents across healthcare customer workflows.
• Develop reliable systems for browser and desktop automation, tool execution, state management, and retry logic.
• Improve agent architecture through experimentation with planning, execution, memory, validation, and recovery mechanisms.
• Build reusable components that enable agents to interact with complex healthcare software systems.
• Develop scalable infrastructure for production AI agent deployments and implement fault-tolerant support for long-running, multi-step workflows.
• Own and develop backend services across a TypeScript and Node.js monorepo.
• Design and maintain APIs, domain services, background jobs, and event-driven systems.
• Build durable workflow orchestration systems, including with technologies such as Temporal.
• Improve backend reliability, fault tolerance, scalability, and performance, and develop reusable engineering primitives.
• Design evaluation frameworks to measure AI agent performance and reliability.
• Build observability and debugging tools to monitor agent execution, diagnose failures, and investigate agent decisions.
• Identify performance regressions, measure improvements, and improve testing, validation, and monitoring for production AI systems.
• Develop automation infrastructure for fragmented healthcare systems, including EMRs, portals, browser and desktop applications, fax workflows, PDFs, and document-processing systems.
• Implement safeguards, validation, and recovery mechanisms appropriate to sensitive healthcare environments.
• Partner with forward-deployed engineers to identify recurring deployment challenges and create scalable platform solutions.
• Collaborate with engineering and product teams on infrastructure priorities and technical architecture.
• Own technical projects from design through implementation, deployment, and ongoing improvement.
• Contribute to engineering standards, architecture decisions, and platform development practices.
• Participate in rapid experimentation and iterative development, helping establish the technical foundations for a growing healthcare AI platform.

Benefits

• Competitive equity package.
• Opportunity for meaningful ownership of foundational platform infrastructure and architecture.
• Professional growth through experience developing production AI infrastructure.
• Opportunity to influence engineering practices and long-term technical direction.

What This Job Offers

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