Hello Patient

Healthcare

Prompting&AIAgentResearchEngineer

$180–230k Austin, Texas, United States FULL TIME
Market Sentiment
HIGH DEMAND

Neural analysis suggests this role is
optimal for Senior candidates.

The Brief

“Prompting & AI Agent Research Engineer at Hello Patient. Skills: Prompt engineering, AI research, Experimental design, LLM tooling. Design structured experiments. Build regression test coverage”

What You'll Achieve.

Make confident, evidence-backed decisions; Turn promising ideas into testable prototypes

Industry & Context.

Healthcare
Problems you'll solve

Troubleshooting prompting problems

What They're Looking For.

Must Have

5+ years experience in prompting, AI research, or applied AI, Advanced degree in research-oriented field, CS, linguistics, cognitive science, stats, or similar, Real prompt engineering experience, Solid experimental design fundamentals, Hands-on experience working with LLMs, Comfort with RAG, agentic architectures, LLM tooling, Ability to evaluate and validate AI system behavior, Clear written findings

Nice to Have

PhD preferred, Experience with voice AI or conversational systems, Research background in prompting techniques, prompt optimization, or evaluation, Time at AI lab, applied AI team, or startup, Familiarity with LLM evaluation frameworks, Published or applied work in prompt design, chain-of-thought

What You'll Do.

Design structured experiments

Build regression test coverage

Create pipeline of validated improvements

Prioritize what gets shipped

Stay current on prompting research

Prototype new approaches locally

Translate experiment results

Build evaluation templates and frameworks

How You'll Work.

Team & Collaboration

Work with Product and Engineering teams; Collaborate with Product team

Communication Scope

Clear written findings

Full Job Description

ABOUT THE ROLE Hello Patient is seeking a Prompting & AI Agent Research Engineer to bring structure and rigor to how we advance our AI. We build Mia, an AI voice agent that handles inbound patient calls for multi-location healthcare providers - and as we grow, we need someone who can help us make more confident, evidence-backed decisions about how Mia evolves. You'll design experiments we can trust, stay close to what's emerging in the research community, and turn promising ideas into something testable. This role sits at the intersection of prompt engineering and applied AI research. You should be comfortable enough technically to prototype and run local experiments independently. Above all, we're looking for someone with deep, hands-on prompting experience - someone who has deliberately engineered prompts to change how a system behaves. WHAT YOU'LL DO EXPERIMENTATION & EVALUATION - Design structured experiments with real controls and statistical rigor - Build regression test coverage so we know when a global prompt change is breaking things across workflows we didn't expect - Create a pipeline of validated, high-confidence improvements engineering can pull from instead of building on faith - Work with the team to prioritize what actually gets shipped based on what the experiments say PROMPTING & AGENT ARCHITECTURE RESEARCH - Own prompt design across Mia's agent workflows - multi-turn, voice-first, healthcare context - Stay current on what's coming out in prompting research, and agent architecture, and bring back ideas worth testing - Prototype new approaches locally before anything touches production - Be the person the Product team comes to when they're stuck on a prompting problem COLLABORATION & KNOWLEDGE SHARING - Work closely with our Product and Engineering teams - understand where Mia is struggling and help decide what's worth experimenting on - Translate experiment results into clear recommendations people can actually act on - Build out evaluation templat

Free ATS check

Applying for this Prompting & AI Agent Research Engineer role?

Most applicants get filtered before a human reads their resume. See if yours makes the cut.

How to Apply on Ashby

  • Ashby is a fast modern ATS — most applications take under 3 minutes.
  • The resume parser is strong; verify parsed experience dates and job titles.
  • Custom screening questions are often scored algorithmically — answer completely.
  • Location field affects geo-based screening; use your actual metro area.

ANONYMOUS · UNFILTERED

What do employees actually say about Hello Patient?

Real rants from real employees. Read before you apply.

Read Company Rants →