Research Engineer II (Trust Technologies)
Core
Build LLM-powered AI agents and multi-agent systems to automate and improve insurance workflows including underwriting, claims, policy servicing, risk assessment, and customer engagement.
Role type
Research Engineer (LLM-powered AI agents)
Builds
Autonomous multi-agent systems, agent tools, evaluation frameworks, and demonstration environments for insurance applications.
Domain
Insurance / InsurTech / Trust Technologies
Deliverable
production ML models
Required skills
Large language models (LLMs), prompt engineering, retrieval-augmented generation (RAG), agent frameworks, multi-agent system design, Python, production-grade AI application development, API development, evaluation pipelines, agent orchestration, AI safety, guardrails, model evaluation, data privacy, explainability, responsible AI practices, system platform development, database technologies.
Preferred skills
Insurance domain experience, financial services experience, prior research or engineering experience in LLMs and AI agents.
Technologies
Python, LLM frameworks, agent orchestration tools, database technologies.
Responsibilities
Translate between business and technical contexts regarding AI and agentic AI concepts; conduct research on LLM-powered AI agents and translate algorithms into working prototypes; collaborate on production-oriented system implementations for key insurance workflows; design and build agent tools and evaluation frameworks; produce technical documentation and research papers on AI agent design and trust mechanisms; engage global partners to track emerging trends in LLMs and InsurTech.
Seniority
Mid-level Research Engineer