AI Architect

About the Role

We are looking for an experienced, hands-on AI Architect to define and own the architecture of EigenRisk's AI-powered product capabilities and intelligent automation systems across the EigenPrism platform.

The ideal candidate has designed and delivered production-grade AI systems at scale and has deep experience with LLM ecosystems, agentic architectures, and enterprise integration patterns. This role sets the technical direction for AI engineering at the company. It covers the reference architectures, standards, and platform foundations that let teams ship reliable, secure, and cost-efficient AI solutions quickly.

The position works closely with product, engineering, data/analytics, security, and business leaders to turn strategic goals and real-world requirements into scalable, governed, and maintainable AI systems.

Key Responsibilities

• Define and own the end-to-end AI architecture, including LLM integration, retrieval, agent orchestration, tool and MCP integrations, and serving infrastructure
• Establish reference architectures, design patterns, and engineering standards for AI systems across product teams
• Architect agentic and multi-agent systems, including MCP-compatible tool ecosystems, workflow orchestration, and human-in-the-loop controls
• Design scalable RAG and knowledge retrieval pipelines, including data ingestion, chunking, embedding strategy, vector/hybrid search, and re-ranking
• Lead model selection and strategy across hosted APIs and open-weight models, weighing quality, latency, cost, and data residency
• Define LLMOps practices: evaluation frameworks, prompt and model versioning, regression testing, observability, and continuous improvement loops
• Build in security, privacy, and responsible AI, including guardrails, prompt-injection defense, PII handling, access control, and auditability for enterprise and multi-tenant environments
• Drive cost and performance optimization through caching, routing, batching, token budgeting, and capacity planning
• Guide build-vs-buy decisions and evaluate emerging AI frameworks, platforms, and vendors
• Lead architecture reviews, produce technical roadmaps, and make sure designs align with overall platform evolution
• Turn proof-of-concepts into hardened, production-ready systems with clear operational SLAs
• Mentor senior and junior engineers and build AI engineering capability across the organization
• Partner with DevOps and platform teams on deployment, scaling, and operational readiness of AI services

Required Skills & Experience

• 812 years in software engineering, platform engineering, or ML/AI engineering, including 3+ years designing and delivering production AI/LLM systems
• Proven record as the technical lead or architect on complex, distributed, cloud-native systems
• Expert proficiency in Python and strong backend, API, and distributed-systems design skills
• Deep hands-on experience with LLM ecosystems, orchestration frameworks (e.g., LangGraph, LlamaIndex, Semantic Kernel, or equivalent), and agentic design patterns
• Strong working knowledge of MCP, tool and function calling, workflow engines, and API-first/event-driven architectures
• Expertise in retrieval systems, vector databases, embeddings, and hybrid search
• Experience designing evaluation, observability, and monitoring for non-deterministic AI systems
• Solid grasp of AI security risks and controls, data governance, and enterprise compliance requirements
• Strong production experience on at least one major cloud (AWS, Azure, or GCP), including managed AI services
• Excellent system design, trade-off analysis, and technical documentation skills

Nice to Have

• Experience with fine-tuning, distillation, or self-hosted model serving (e.g., vLLM, TGI, Triton)
• Familiarity with Kubernetes, containerization, IaC, and CI/CD for AI workloads
• Exposure to geospatial data, catastrophe modeling, risk analytics, insurance/reinsurance, or fintech
• Background building multi-tenant enterprise SaaS platforms
• Contributions to open-source AI projects, publications, or conference talks

Ideal Candidate Profile

• Strategic thinker who stays hands-on: can set the architecture and write the code that proves it
• Balances innovation with production rigor, reliability, and governance
• Brings clarity and alignment to complex technical decisions across teams
• Strong influencer and communicator with both engineering and business stakeholders
• Passionate about applied AI and about turning emerging technology into real customer value