SOUTH JORDAN, UT2 days ago
Responsibilities Agentic Framework Evaluation Design and run evaluations for LLM-based agents (quality, reliability, safety) Analyze agent behavior and identify failure modes Propose improvements based on empirical results Agentic Platform Development Build and enhance components such as tools, skills, memory systems, and MCP integrations Improve orchestration, observability, and developer experience Prototype new capabilities for real-world workflows Neural-Symbolic AI (Healthcare Focus) Explore approaches combining LLMs with rules, knowledge graphs, or symbolic reasoning Work on use cases requiring auditability and explainability (e.g., claims, policy logic) Help bridge probabilistic AI with deterministic systems Forward-Deployed Engineering Experiments Partner closely with internal stakeholders or pilot users Rapidly prototype and iterate on solutions in real-world contexts Help define patterns for scaling adoption of agentic systems This job description is intended to describe the general nature and level of work being performed and is not to be construed as an exhaustive list of responsibilities, duties and skills required. Qualifications Currently pursuing a Bachelor's degree (Freshman-Senior) in related field Hands-on experience with Python or similar programming languages Familiarity with LLMs / GenAI (e.g., building projects with OpenAI, Claude, Gemini, or open-source models) Strong curiosity and willingness to learn quickly in ambiguous environments Ability to break down problems and iterate through experimentation Cognitive/Mental Requirements: * Communicating with others to exchange information.