Senior Applied AI Engineer

Senior Applied AI Engineer role supporting the build and hardening of production agent systems for a regulated insurance environment. This is a senior individual contributor position with meaningful architectural and organizational influence, including work to define AI-first engineering and product principles for a multi-tenant, API/MCP-first platform.

Responsibilities

• Design and ship production agentic systems, including multi-agent orchestration, tool use, RAG pipelines, and MCP-based integrations against platform APIs.
• Build a reliability layer around agents through evals, guardrails, observability, cost controls, and regression testing to ensure agent behavior is measurable and defensible.
• Implement maker-checker patterns so AI accelerates regulated workflows without autonomously touching money, binding, or compliance decisions.
• Integrate agent capabilities with the deterministic core, including the canonical data model, Config Hub, and Control Tower task orchestration.
• Co-author and implement AI-first engineering principles such as agent harnesses, AI-assisted code review, shared skills and prompt libraries, eval-gated CI, and dev-environment standards, then drive adoption across squads in Vilnius and the US.
• Shape AI-first product principles, including where AI belongs in the product and where it does not, human-in-the-loop patterns, agent UX conventions, and how AI capability estimates affect scoping and build-versus-buy decisions.
• Set the standard through own delivery by demonstrating what AI-first engineering enables and establishing reference patterns others adopt.
• Work with engineering leadership on the AI architecture roadmap and year-end production proof points.
• Perform other duties as requested, directed, or assigned.

Requirements

• 5+ years of software engineering experience with strong backend or full-stack foundations, including APIs, event-driven systems, and data modeling.
• Real production experience with LLM-powered systems, including agent orchestration, tool calling, RAG, and structured outputs (not only prototypes or demos).
• Demonstrated ability to make agentic systems reliable using evals, fallbacks, deterministic checkpoints, and cost and latency management.
• Strong product judgment to scope AI where it earns its place while defaulting to deterministic code where it does not.
• Evidence of changing how others build, such as workflows, harnesses, or practices introduced that teams adopted and continued using.
• Clear written communication and comfort working in an async-first, distributed team environment.

Technologies

• LLM-powered systems
• RAG
• APIs
• MCP
• Tool calling
• Structured outputs
• Event-driven systems

Benefits

• Health, dental, and vision plans.
• Amazing work-life balance with 4 weeks of Paid Time Off.
• 10 Paid Company Holidays with 2 floating holidays.
• 401K programs with employer match.
• Personal assistance programs for support in a healthy personal and work life.

Compensation Range

USD 140,000 - 170,000 per year

Location

Remote

About the Role Context

This position focuses on building and hardening production agent systems in a regulated insurance domain, while helping define AI-first engineering and product principles for a multi-tenant, API/MCP-first platform. The role is designed for an individual contributor who can drive architectural direction and adoption across squads in Vilnius and the US.