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 building vertical insurance agents and the shared horizontal capabilities they compose from, such as RAG, retrieval and instructional flows.
• ▹Define and enforce levels of autonomy, assistive, semi-autonomous, autonomous, with explicit human-in-the-loop checkpoints and escalation paths.
• ▹Drive the MCP strategy: which capabilities EIS exposes as MCP servers, how agents consume external MCP tools, and the tool registry and versioning.
• ▹Maintain the multiple-stack approach, TypeScript and Java, and help teams pick the right stack per agent.
• ▹Lead Architecture Decision Records for agentic capabilities; partner with Platform, Security and DevOps so agents are observable, testable, sandboxed and compliant by default.
• ▹Drive AI DevOps for agents: trace capture and replay, eval harnesses, prompt and model versioning, cost and latency budgets, and progressive rollout strategies.
• ▹Set safe-AI standards for agentic systems: prompt injection and tool-poisoning defenses, action allow-lists, blast-radius controls, PII handling, data residency and 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 or prototypes, with meaningful autonomy and multi-step tool use.
• ▹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 with the Java/Spring ecosystem.
• ▹Strong with TypeScript and Python for AI, LangChain, LangGraph or an equivalent agent framework, production experience required.
• ▹Hands-on with vector databases.
• ▹Sharp instinct for when an agent is the right answer and when a deterministic workflow is.

Soft skills

About the company

EIS Group builds insurance software platforms and is developing an agentic AI platform to automate insurance workflows end-to-end across Policy, Billing and Claims.