SlipstreamJobs tracks this role from the company's public career site. Apply directly on the employer's site.
Hippocratic AI is seeking a Forward Deployed Engineer to own the technical delivery of AI deployments that transform healthcare operations. You will embed with health system customers to design, build, launch, and operate production conversational AI agents that handle real clinical workflows and impact thousands of patient interactions.
In your first 90 days, you will complete end-to-end ownership of your first AI deployment: design and implement a RAG pipeline grounded in customer clinical data, build tool-calling and Model Context Protocol (MCP) integrations connecting agents to customer systems (EHRs, data warehouses, operational tools), execute a production go-live, and establish monitoring systems. By 12 months, you will have deployed multiple agents across assigned health systems, built reusable AI patterns and frameworks, become the trusted technical partner for solving complex AI problems, and generate measurable evidence of operational and clinical impact.
Key responsibilities include:
- Designing and implementing RAG pipelines that ground conversational AI in customer clinical data while managing retrieval latency and data governance
- Building tool-calling and MCP architectures enabling secure AI agent interactions with EHRs (Epic, Cerner, Athena), data warehouses, and operational tools
- Developing production Python code using LangChain, LangSmith, and modern AI frameworks to implement advanced LLM techniques (RAG, prompt engineering, LLM-as-judge, chain-of-thought reasoning)
- Executing end-to-end deployments including infrastructure setup, integration testing, production monitoring, cutover planning, and go-live execution
- Monitoring and owning production systems through instrumentation, incident response, troubleshooting, and implementing reliable fixes
- Partnering with customers as technical expert to explain AI architecture, build confidence in solutions, and solve their hardest AI problems
You will work alongside Deployment Strategists, engineers, and clinical experts, embedded with customers but tightly connected to the core AI team. The role offers high technical ownership and autonomy with direct access to product, ML research, and engineering leadership. This is a culture of shipping real systems, owning outcomes, and solving problems proactively.
The role is based in the United States (any of 41 states except Alaska, Connecticut, Delaware, North Dakota, West Virginia, New Mexico, and Hawaii) with 25-40% travel requirements.
REQUIREMENTS:
- Bachelor's degree in Computer Science, Software Engineering, or related technical field
- 3+ years of professional software engineering experience with strong Python fundamentals and production software development experience
- Hands-on experience with LLM frameworks (LangChain, LangSmith, or similar) and deep understanding of modern LLM development patterns and best practices
- Deep expertise in LLM techniques including retrieval-augmented generation (RAG), prompt engineering, tool calling, LLM-as-judge, and related advanced patterns
- Demonstrated experience building integrations with APIs, databases, or enterprise systems; comfort with async patterns, error handling, and reliability engineering
PREFERRED QUALIFICATIONS:
- Experience with Model Context Protocol (MCP) or similar frameworks for tool integration and multi-system orchestration
- Healthcare IT experience, including EHR integrations (Epic, Cerner, Athena), FHIR, HL7, or healthcare data standards
- Production DevOps or infrastructure experience, including setting up monitoring, alerting, logging, and incident response systems
- Track record deploying AI systems or working with LLMs in production environments, managing latency, reliability, and operational complexity
- Experience in mission-critical or safety-sensitive systems where reliability and error handling are non-negotiable
- Startup or high-growth technology background, particularly in technical leadership or ownership roles
