MAPFRE is seeking an hands-on Agentic AI Engineer to design, build, and ship production-grade AI agents for high-impact insurance workflows, including underwriting and claims. This role focuses on end-to-end ownership across agent architecture, backend services, evaluation, guardrails, and scalable deployment.
Role Summary
You will develop reusable agent components and engineering patterns that help accelerate future solutions. Responsibilities span technical feasibility decisions across deterministic rules, traditional machine learning, plain GenAI, and autonomous agents, with attention to cost, reliability, and measurable outcomes.
Key Responsibilities
- Design, build, and deploy AI agents and multi-step agentic workflows for complex insurance processes such as underwriting and claims, creating reusable components and repeatable engineering patterns.
- Convert business and solution designs provided by the AI architect and product owner into working agents, advising on technical feasibility, cost, and reliability trade-offs across approaches.
- Implement agents as well-defined backend services (for example, FastAPI) with stable API contracts, secure authentication, resilient error handling, and automated testing.
- Integrate agent services with enterprise systems, data sources, and external APIs through tools and MCP servers.
- Own agent quality through continuous improvement by defining success criteria, building test datasets, performing automated evaluations, diagnosing failures, and applying targeted fixes.
- Implement guardrails, human-in-the-loop checkpoints, action limits, observability, monitoring for performance and reliability, cost controls, and audit logging aligned with AI governance and regulatory requirements.
- Collaborate across business and technical teams to prototype quickly, including lightweight MVP interfaces (such as Streamlit), then validate, deploy, and scale solutions using cloud, containerization, and CI/CD practices.
- Measure technical performance and business value, and communicate results and limitations to both technical and non-technical stakeholders.
Required Qualifications
- Bachelor’s degree in Computer Science, Engineering, or a related quantitative field, with either 7+ years of software, machine learning, or data engineering experience, or a Master’s degree with 5+ years of relevant experience.
- 2+ years of hands-on experience building LLM-based applications, including at least one agentic system (tool calling, multi-step workflows, and related capabilities) deployed to production and used by real users.
- Strong Python skills and sound software engineering fundamentals, including API and tool integration, automated testing, error handling, version control, and debugging in non-deterministic systems.
- Hands-on experience with at least one agent framework or SDK, with LangGraph strongly preferred, and experience using major model APIs or managed AI platforms such as Amazon Bedrock to build production AI agents integrated with tools, APIs, and enterprise systems.
- Experience evaluating LLM applications or agents, including test datasets, metrics, regression testing, and appropriate use of model-based evaluators.
- Practical understanding of agent reliability and security risks, strong problem-solving skills, and the ability to determine where an agentic approach is appropriate. Demonstrated ability to solve ambiguous, complex problems with minimal direction, high autonomy, a results-driven mindset, and persistence to find root causes.
- Strong communication skills to partner with architects and business experts and explain agent behavior and limitations to non-technical stakeholders.
Technologies
- Python
- FastAPI
- Streamlit
- LangGraph
- Amazon Bedrock
- MCP
Preferred Skills
- Insurance domain knowledge, with claims or underwriting experience as a strong plus.
- Experience deploying production AI applications to the cloud, with AWS preferred, including use of containers and CI/CD.
- Experience with retrieval-augmented generation (RAG), context engineering, structured outputs, and integrating agents into enterprise systems via APIs and MCP.
- Experience mentoring team members and influencing best practices across teams.
Benefits
- Paid Time Off (PTO) with a flexible PTO program.
- 401(k) & Profit Sharing with company matching contributions up to certain amounts.
- Medical, Dental and Vision coverage.
- STD, LTD, Life Insurance, FSA, HSA, and various wellness programs.
Location & Salary
- Location: Webster, MA (hybrid)
- Salary: USD 121,000 - 191,000 per yearly
Compensation Transparency
The typical starting salary range for this role is determined by factors including skills, experience, education, certifications, and location. Some roles at MAPFRE may be eligible for commission and/or bonus earnings in addition to salary. Salary Range: $121,000-$191,000.
Why MAPFRE
- Purpose & Culture: Join a company built on trust, collaboration, and inclusion.
- Career Growth: Tuition reimbursement, leadership programs, and internal mobility opportunities.
- Social Responsibility: Contribute to meaningful initiatives through Fundación Mapfre, supporting communities and sustainability worldwide.
