Lead AI System Architect

Stack

Responsibilities

• ▹Own the architecture of EIS's agentic platform: agent orchestration, MCP-native tool ecosystems, agent memory, planning, and tool/function calling patterns
• ▹Enable and support domain teams for vertical insurance agents and shared horizontal capabilities (RAG, retrieval, instructional flows)
• ▹Define and enforce levels of autonomy (assistive, semi-autonomous, autonomous) with human-in-the-loop checkpoints, escalation paths, and reversibility
• ▹Drive the MCP strategy: which capabilities EIS exposes as MCP servers, how agents consume external MCP tools, tool registry and versioning
• ▹Maintain the multi-stack approach (TypeScript and Java), helping teams pick the right stack per agent
• ▹Lead Architecture Decision Records (ADRs) for agentic capabilities, partnering with Platform, Security, and DevOps
• ▹Drive AI DevOps for agents: trace capture and replay, eval harnesses, prompt/model versioning, cost and latency budgets, progressive rollout
• ▹Set safe-AI standards: prompt injection and tool-poisoning defenses, action allow-lists, blast-radius controls, PII handling, data residency, bias mitigation
• ▹Translate insurance use cases into production agent designs with product strategists and domain architects; provide technical leadership and mentorship

Requirements

• ▹Proven track record designing and shipping agentic systems in production — not demos, not prototypes
• ▹Strong systems background: data-intensive, distributed, latency-sensitive design in production environments
• ▹Deep, hands-on experience with agent patterns: orchestration, planning, ReAct-style and graph-based agents, agent memory, tool/function calling, MCP, structured outputs
• ▹Strong Java/Spring ecosystem knowledge
• ▹Strong TypeScript and Python for AI (LangChain, LangGraph, or equivalent) — production experience required
• ▹Hands-on experience with vector databases

Soft skills