Director, AI Solutions Engineer

Join our AI & Engineering team in transforming technology platforms, driving innovation, and making a significant impact on our members' success. You will work alongside talented professionals reimagining and re-engineering operations and processes that are critical to our business — from underwriting and claims to member experience and risk management.

Your contributions will help PURE improve operational performance, accelerate new digital capabilities, and fuel growth through innovation. Our AI & Engineering practice leverages cutting-edge engineering to build, deploy, and operate integrated solutions across software, data, AI, and cloud infrastructure — all in service of members who expect more from their insurance company.

This role is hands-on and delivery-oriented. You will ship production pipelines, APIs, agents, and containerized services that support model training, real-time inference, RAG, and LLM-powered applications using Claude Code, OpenAI Codex, GitHub Copilot, AWS ECS, AWS AgentCore Gateway, AWS AgentCore Harness, and Databricks. You will help turn AI concepts into governed, observable, secure, and cost-effective production systems. You will work in close partnership with the Lead AI Solutions Architect and AI Data Engineer to bring AI-powered products from design to production.

Tools, Platforms & Engineering Environment

This role will work with the AI engineering stack PURE is actively building and scaling, including Claude Code, OpenAI Codex, GitHub Copilot, AWS ECS, AWS AgentCore Gateway, AWS AgentCore Harness, and Databricks.

The engineer will help build and deploy production AI applications as containerized services, including AI agents, copilots, knowledge assistants, RAG-based applications, and model-powered workflows. This includes integrating LLMs with enterprise tools and data sources, defining reusable agent skills and tool interfaces, building governed knowledge bases, and deploying AI workloads with strong security, observability, and cost controls.

Strong candidates will have hands-on experience with Python, APIs, containerized applications, cloud-native deployment patterns, LLM application development, agent orchestration, RAG, evaluation frameworks, and modern AI-assisted engineering tools. Experience with LangChain, LangGraph, open-source model fine-tuning or adaptation, and Databricks-based AI/ML workflows is highly valuable.

Build & Deploy AI Solutions

• Partner with the Lead AI Solutions Architect and AI Data Engineer to design, build, and deploy secure, scalable AI solutions: APIs, services, pipelines, agents, containers, and serverless functions that meet availability, performance, and security requirements. Deploy AI workloads primarily using cloud-native patterns, including AWS ECS-based containerized applications.
• Build and operationalize LLM-enabled products including copilots, knowledge assistants, summarization engines, policy Q&A tools, and agentic workflows using Claude Code, OpenAI Codex, GitHub Copilot, AWS AgentCore Gateway, AWS AgentCore Harness, Databricks, and comparable LLM platforms. Apply thoughtful prompt and context patterns, tool/function calling, reusable agent skills, and agentic orchestration patterns..
• Implement RAG, knowledge base, and document intelligence patterns end-to-end: ingestion, chunking, embeddings, vector and hybrid search, retrieval evaluation, and telemetry. Build and maintain Databricks-backed knowledge bases and AI agent capabilities where appropriate.
• Deliver governed data and features for ML and GenAI — curated datasets, feature pipelines, and feature serving — supporting both training workflows and real-time inference with consistency, caching, backfill support, and latency SLOs.
• Build reusable AI agent skills, tool definitions, prompts, guardrails, and orchestration patterns that can be shared across PURE’s AI products and engineering teams.
• Use LangChain, LangGraph, or comparable frameworks where appropriate to build agent workflows, tool-use orchestration, stateful reasoning patterns, and multi-step automation.

Governance, Trust & Safety

• Implement trust, safety, and governance controls including PII handling, prompt-injection defenses, content filtering, and policy-based access controls — built in close partnership with security and risk teams.
• Ensure AI outputs are auditable, explainable, and compliant with applicable regulatory requirements (SOC 2, NAIC, GDPR) — a non-negotiable in insurance.
• Define and maintain data lineage and model versioning practices so every production inference can be traced, reproduced, and reviewed.
• Develop evals and red-teaming protocols to proactively identify failure modes in