Agentic Workflows - Backend Engineer (Full stack)

Job Description

Job Description

We’re looking for a senior, hands-on software engineer to design, build, and operate LLM-powered and agentic workflows that support real production use cases—not research demos.

This role sits at the intersection of backend engineering, applied AI, and production infrastructure. You’ll work on systems that handle sensitive healthcare data, integrate AI into user-facing workflows, and run reliably at scale under strict security and compliance constraints.

This is an individual contributor role with high ownership. You’ll be expected to make pragmatic technical decisions, collaborate closely with product and operations, and help shape how AI capabilities are integrated into the broader platform.

What You’ll Be Doing

• Designing and operating LLM-powered and agentic workflows end-to-end

• Integrating AI capabilities into backend and product workflows

• Building and maintaining secure, compliant systems for sensitive healthcare data

• Making technical decisions around security, compliance, cost, performance, and scalability of AI workloads

• Implementing monitoring, alerting, and observability for AI pipelines and production services

• Collaborating cross-functionally with engineering, product, and operations teams

• Mentoring engineers on backend best practices and applied AI workflows

Must-Haves

• 5+ years of professional software engineering experience

• Strong backend and/or full-stack engineering background from B2B SaaS or product-driven startups

• Experience deploying secure, reliable systems on cloud platforms (AWS, GCP, or Azure)

• Demonstrated ability to build and operate production systems, not just prototypes

• Comfort working with non-engineers and translating product requirements into technical solutions

• Hands-on experience integrating LLMs into real applications (prompting, orchestration, evaluations, or agents)

This role favors engineers who have owned AI workflows in production, not candidates coming purely from research, data science, or director-level roles.

Nice-to-Haves

• 1+ year of experience designing AI workflows end-to-end in production

• Experience leading AI infrastructure or platform projects at an early-stage startup

• Contributions to engineering architecture or coding standards

• Experience with containerization and orchestration (Docker, Kubernetes)

• Infrastructure-as-code experience (Terraform, Pulumi)

• Exposure to early-stage product ideation for AI-enabled features

  What This Role Is (and Isn’t)

  • A senior IC role with strong ownership

  • Applied AI + backend engineering, focused on real users and real constraints

  • Startup environment with cross-functional collaboration

  • Not a director-level or people-management role

  • Not an AI research or purely scientific role

  • Not suitable for candidates without hands-on LLM or agentic workflow experience

  • Not remote-only or relocation-friendly

  Location & Work Setup

  • Location: New York City

  • Work model: Hybrid (in office Monday, Wednesday, Thursday)

  • Relocation: Not available

  • Visa sponsorship: Available

  Compensation

  • Base salary: $190,000 – $250,000

  • Equity: Offered (details TBD)