Lead AI System Architect

This is a fully remote position, open to applicants in United Kingdom.

📋 Description

• Take ownership of the architecture for EIS's agentic platform, which includes agent orchestration, MCP-native tool ecosystems, agent memory (short-term, long-term, semantic), planning, and reusable tool/function calling patterns across product domains.

• Facilitate and support domain teams focusing on vertical insurance agents and the horizontal capabilities (RAG, retrieval, instructional flows) they develop.

• Establish and enforce autonomy levels — assistive, semi-autonomous, autonomous — with clear human-in-the-loop checkpoints, escalation paths, and reversibility for high-stakes actions within regulated workflows.

• Lead the MCP strategy, determining which capabilities EIS exposes as MCP servers for internal and partner agents, how our agents utilize external MCP tools, and the tool registry, schemas, and versioning that ensure scalability.

• Uphold the multiple stack approach as a key capability: Typescript and Java. Guide teams in selecting the appropriate stack for each agent while ensuring alignment through shared configuration artifacts, prompt management, and evaluation tooling.

• Direct Architecture Decision Records (ADRs) for agentic capabilities, collaborating with Platform, Security/InfoSec, and DevOps to ensure agents are observable, testable, sandboxed, and compliant by default.

• Spearhead AI DevOps for agents: encompassing trace capture and replay, evaluation harnesses (task success, tool-use correctness, regression), prompt and model versioning, cost and latency budgets per agent, and progressive rollout strategies.

• Establish safe-AI standards for agentic systems that include defenses against prompt injection and tool-poisoning, action allow-lists, blast-radius controls, PII handling, data residency, and bias mitigation, treating agent safety as a primary architectural concern.

• Transform insurance use cases into operational agent designs in collaboration with product strategists and domain architects; provide technical leadership and mentorship; articulate agentic trade-offs (autonomy, reliability, cost, safety) effectively to executives, customers, and engineers.

⛳️ Requirements

• Proven experience in designing and deploying agentic systems in production, with a focus on meaningful autonomy and multi-step tool usage — no demos or prototypes.

• Strong background in systems design, particularly in data-intensive, distributed, and latency-sensitive production environments.

• Extensive hands-on experience with agent patterns, including orchestration, planning, ReAct-style and graph-based agents, agent memory, tool/function calling, MCP, and structured outputs. Possess a keen instinct for identifying when an agent is appropriate versus a deterministic workflow. Stay informed on industry advancements and translate them into the roadmap.

• Proficient in the Java/Spring ecosystem.

• Skilled in Typescript and Python for AI (LangChain, LangGraph, or similar agent frameworks) with required production experience. Comfortable working in both technology stacks.

• Practical experience with vector databases, including embedding models, hybrid search, re-ranking, and retrieval evaluation.

• Familiar with agent evaluation and observability techniques, such as traces, replays, eval harnesses, guardrails, and cost/latency telemetry. Knowledgeable in AI configuration-as-code.

• Experience in deploying AI services on cloud platforms (AWS, Azure, GCP) in regulated enterprise environments, including security reviews, data residency, and audit trails.

• Familiarity with the insurance, financial services, or other regulated sectors is an advantage.

• Strong architectural judgment, balancing build vs. buy, vendor vs. in-house, agent vs. deterministic workflow, model selection, and total cost of ownership.

• Exceptional written and verbal communication skills, capable of making agentic trade-offs understandable to non-AI audiences.

• An advanced degree in Computer Science, AI/ML, or a related field, or equivalent practical experience.

🏝️ Benefits

• Collaborate with top talent and exceptional colleagues who are experts in their respective fields and technologies.

• Work within a Scaled Agile environment with diverse, multicultural, and cross-functional teams.

• Be part of a global and modern software product company that develops world-class Enterprise InsurTech products powered by state-of-the-art technologies (microservices, reactive, cloud, continuous delivery).

• Enjoy flexible working hours and the option for remote work.

• Participate in an employee referral program.

• **Incentives and Benefits Allowances:**

• Mobile phone and Internet allowance.

• **Benefits:**

• Pension plan based on a Group Pension Scheme.

• Medical/Dental/Optical Health Insurance for you and your dependents.

• Income Protection.

• Death in Service coverage.

• Travel Insurance.

• **[All pay components are based on objective, gender-neutral criteria within EIS’s Compensation Policy.]**