Forward Deployment Engineer

Role Mission

As HAI's Forward Deployed Engineer (FDE) Resident, you will own the delivery of safe, autonomous clinical conversations with patients, from the conversation layer to the integration design. You'll develop and refine the prompts and conversation logic that determine how millions of patients experience our breakthrough healthcare AI. And you'll architect the transports and mappings to get data in and out of these conversations. This role exists because building truly autonomous clinical conversations requires both deep technical skill and relentless focus on patient experience—and we need someone who can master both.

What You Will Accomplish

Own your first major outcome: By day 90, you will have shipped improvements to at least two live conversation workflows, developed advanced prompts that meaningfully improve clinical safety scores or patient satisfaction metrics, collaborated with clinicians to translate their feedback into conversation logic, and shipped code that's now running in production healthcare environments.

Drive lasting impact: This is the front door to our Forward Deployed Engineer (FDE) track: your first 6 months are as an FDE Resident, followed by 6 months as an Associate FDE, working alongside FDE leadership with exposure to Product Engineering and AI Engineering along the way. Most residents graduate into full FDE roles, with some moving into Engineering or Product based on their strengths and interests.

The Team

You'll work alongside software engineers, ML scientists, product managers, and clinical experts who are obsessed with getting conversation right. This is a collaborative team that ships fast, values experimentation, and treats patient safety as non-negotiable. You'll have direct input into product decisions and the autonomy to innovate on conversation and integration design.

What You Will Do

• Develop advanced prompts for our conversation planning layer using sophisticated prompting techniques (chain-of-thought, few-shot learning, role-based prompting, structured outputs) to enable complex agentic workflows that handle real clinical scenarios
• Engineer conversation logic and patient interactions that balance clinical accuracy, safety guardrails, and patient experience—writing, testing, and iterating on prompts that make our agents feel natural and trustworthy
• Design and build the integrations that connect our conversational agents to customer EHRs, scheduling systems, and telephony platforms—turning HL7/FHIR feeds and REST/webhook APIs into the real-time signals that shape every conversation
• Collaborate with clinicians, product managers, and engineers to translate clinical requirements into conversation designs, conduct user testing with healthcare professionals, and iterate based on feedback from real-world usage
• Conduct rigorous experiments and analysis on model outputs, prompt variations, and conversation strategies—measuring impact on clinical safety scores, patient satisfaction, task completion rates, and other key metrics
• Use advanced prompting techniques including retrieval augmentation, tool calling, conditional logic, and multi-turn conversation management to optimize model performance and patient experience across diverse clinical scenarios
• Maintain and improve our conversation codebase, ensuring prompts are version-controlled, documented, and deployed safely to production healthcare environments with proper testing and rollout procedures
• Sit shoulder-to-shoulder with customer engineering teams during go-lives, debugging integration issues live and turning one partner's edge case into a reusable pattern that ships to every future customer

Location Requirement

We believe the best ideas happen together. To support fast collaboration and a strong team culture, this role is expected to be in our Palo Alto office five days a week, unless otherwise specified.

Basic Qualifications

• Bachelor's degree in Computer Science, Computer Engineering, Software Engineering, or a related technical field (or equivalent demonstrated coursework and professional projects)
• 2+ years of professional industry experience in software development, AI/ML, or related technical roles
• Strong Python proficiency with hands‐on experience writing production or near-production code
• Demonstrated experience with LLM prompting through professional work or substantial personal projects (ChatGPT, Claude, or similar models)
• Experience building integrations with databases and RESTful APIs, including understanding of async patterns and error handling
• Strong problem‐solving mindset with proven ability to break down complex problems and iterate toward solutions

Preferred Qualifications

• Experience with backend development frameworks (Flask, Django, FastAPI, Spring Boot, or similar)
• Portfolio of pe