Forward Deployed Engineer
Posted 13
views
Summary
Medeloop is hiring a Forward Deployed Engineer to deploy its AI agent platform into customers' cloud environments, build connectors (data lakehouses, internal APIs, EHR data via FHIR), and turn clinical/research procedures into agent workflows, owning each deployment end to end. Core stack: LLM APIs and agentic systems, coding agents (Claude Code, Codex, Cursor), cloud infrastructure, and data lak
The Role
As a Forward Deployed Engineer, you’ll deploy Medeloop’s systems and products into the customer’s cloud where their data sits, connect them to the tools their teams already use, and build bespoke clinical and research workflows on top, with our platform as the spine. You’ll work side by side with researchers, analysts, data engineers, and security teams, and you’ll own each deployment from the first scoping call to production. You’re the person who turns a first deployment into a lasting customer.
Key Responsibilities:
- Deploy Medeloop’s systems and products in each customer’s cloud with infrastructure as code and our deployment pipeline.
- Build the connectors and tools the agent calls, from lakehouse tables and internal APIs to EHR data over FHIR.
- Turn a team’s procedures, definitions, and business logic into agent workflows and playbooks on Medeloop’s products, so the agent works the way that team works.
- Define evaluations and launch criteria with the customer, test against answers their experts trust, and ship only when the workflow meets them.
- Scope each workflow with the customer, estimate the effort, build, test, take it live, and measure it against the success criteria you agreed on.
- Bring a security-first mindset to everything you build. You’ll work with sensitive patient data in a highly regulated environment under HIPAA, and you’ll walk customer security teams through private connectivity, access controls, and PHI handling, explaining precisely what stays in their environment and what returns.
- Turn custom builds into reusable connectors, playbooks, and platform features, and bring what you learn in the field back to product and engineering. Hold the line on one-off requests that won’t make the product better.
- Monitor the workflows you ship, fix what breaks when customer systems change, and improve them as usage grows.
- Join discovery and scoping conversations with our leadership, and help size the work before it’s priced.
Who You Are:
- Experience building scalable agentic systems that carry out long-horizon, multi-step tasks, and designing the evaluation frameworks that show they work reliably.
- Experience building with LLM APIs, including tool calling, MCP or similar protocols, prompt and workflow design, and evaluations.
- Deep, day-to-day fluency with coding agents such as Claude Code, Codex, and Cursor, and a track record of using them to ship high-quality code fast.
- Hands-on experience with major cloud providers and their infrastructure.
- Experience with data lakehouses and warehouses.
- An extremely clear communicator, in writing and in person, with technical and non-technical audiences alike.
- Confidence in a room with a researcher, a data engineer, and a CISO, and the ability to turn ambiguous requests into scoped, shippable work.
- Comfort with autonomy and ambiguity, the judgment to move fast without cutting corners on security, and a willingness to travel to customer sites.
- Fearlessness about learning, with the eagerness to dive into bespoke workflows and niche concepts you’ve never seen before and to take on ambitious projects outside your past experience.
- Nice to have: Experience with EHR, claims, OMOP, or FHIR data, and work under HIPAA or in another highly regulated deployment environment; forward-deployed, solutions, or implementation engineering, ideally at a startup; and containers and sandboxing. A clinical or healthcare background is not required.
Why Medeloop
- Ownership from day one: small team, high-trust, no layers between your work and its impact
- Technically ambitious: you'll build AI-powered workflows, not just support them
- Real-world stakes: your work accelerates drug development, addresses health equity, and improves clinical research for institutions that matter
- Strong foundation: Series A, top-tier investors, and a data asset (200M+ patient records) that most companies spend years trying to build
Skills
As published by greenhouse · 8 questions · 4 written answers
Basics
First Name, Last Name, Email, Phone, Resume/CV, Cover Letter
Short answers (1)
- Preferred First Name optional
Pick from a list (3)
- Are you currently based in the San Francisco Bay Area and open to working in a hybrid model? (Please note: this role is limited to candidates already located in the area, as we do not offer relocation support.)
- Do you require visa sponsorship?
- Are you willing to undergo a background check in accordance with local laws and regulations?
Written answers (4)
- Can you walk us through a production agentic AI system you’ve built end-to-end — what was the architecture, what agentic frameworks did you use, and what were the key challenges you faced in making it reliable?
- How have you approached building evaluation and safety frameworks for autonomous agents — specifically, how do you test for reliability, factuality, and safety in a regulated or high-stakes domain like healthcare?
- Describe your experience fine-tuning or working with large language models on domain-specific datasets — what was the use case, how did you handle data quality and compliance considerations, and how did you measure success?
- This role requires influencing technical strategy while staying hands-on with building. Can you give an example of a time you shaped a product or engineering direction from the ground up, and how you balanced rapid experimentation with the need for production-quality, compliant systems?
