AI Engineer – AI Agents (Healthcare)
Core
Design, evaluate, and scale LLM-powered agents for healthcare workflows, building datasets, evaluation systems, and feedback loops to ensure reliability and safety.
Role type
Mid-level AI Engineer (LLM Agents & Evaluation)
Builds
LLM-powered agents, evaluation pipelines, and internal tooling for model monitoring and iteration.
Domain
Healthcare + Generative AI / LLM Engineering
Deliverable
production ML models
Required skills
LLM engineering, prompt engineering, evaluation frameworks, dataset creation, system design, Python, APIs, cloud environments, automation pipelines, latency optimization, conversational design
Preferred skills
Voice AI, speech technologies, real-time agent systems, fine-tuning, retrieval strategies
Technologies
Python, JavaScript, LLMs, cloud platforms
Responsibilities
Build and maintain agentic workflows and training/evaluation datasets; Run systematic LLM evaluations and track regressions; Define and implement performance metrics (correctness, latency, hallucination control, safety); Collaborate with Product and Customer teams to align agent behavior with user expectations; Develop internal tooling for evaluation, annotation, and iteration; Build automated pipelines for regression checks and model monitoring; Debug complex system behaviors spanning prompts, tools, and APIs; Translate customer insights into model needs and product improvements; Tune latency and conversational naturalness for voice AI systems.
Seniority
Mid-level, hands-on IC
