LEAD AI ENGINEER — New York, NY
Зарплата не указана
ОткликнутьсяКомпания: ••••••••
Локация: New York, NY
Формат: не указан
Занятость: Полная занятость
Грейд: Lead / руководитель
E6B bsaKkhH8urZ - LEAD AI ENGINEER
Generative AI | AI Agents | RAG | Azure AI Foundry | Databricks | MLflow
Experience
10+ years
Role Level
Lead AI Engineer
Primary Platforms
Microsoft Azure and Azure Databricks
Domain
Insurance and Benefits Management
Role Summary
Seeking a hands-on Lead AI Engineer with 10+ years of experience in software, data or machine-learning engineering, including leadership of enterprise AI delivery and proven experience building production-grade AI assistants. The role will design and deliver secure, governed generative AI, retrieval-augmented generation, conversational and agentic solutions using Microsoft Azure and Azure Databricks, supported by Insurance and Benefits Management domain experience.
Key Responsibilities
• Lead AI solution architecture, detailed design and engineering standards for generative AI, RAG, agents and machine-learning services.
• Design agent orchestration, routing, tools and workflow patterns using Azure AI Foundry and Databricks agent capabilities.
• Design and build enterprise AI assistants using conversation orchestration, session context, tool calling, document and structured-data retrieval, vector and semantic search, citations, guardrails and abstention patterns.
• Integrate approved LLM and embedding endpoints through governed AI gateways and enterprise APIs.
• Develop assistant prompts, system instructions, conversation flows, tools, AI functions, APIs and reusable components using Python, SQL and modern AI frameworks.
• Create golden conversation datasets and automated tests for assistant task completion, grounding, factuality, retrieval quality, safety, role isolation, latency and cost.
• Implement MLflow experiment tracking, prompt/model/agent versioning, tracing, evaluation and release evidence.
• Apply tenant and role isolation, managed identities, secrets management, prompt-injection defenses, auditability and human approval controls.
• Operationalize AI services with CI/CD, monitoring, token and cost telemetry, failure handling, rollback and production support.
• Lead code and design reviews, mentor AI engineers and collaborate with architecture, data, product, security, QA and DevOps teams.
Mandatory Technical Skills
Python; SQL; generative AI and LLM application engineering; enterprise AI assistants and conversational AI; multi-turn conversation design; session and context management; agentic AI and tool calling; retrieval-augmented generation; prompt and system-instruction engineering; embeddings, chunking and vector search; Azure AI Foundry; Azure OpenAI or approved LLM APIs; Azure AI Search; Azure Databricks; Databricks Genie and agent capabilities; MLflow tracking, tracing and evaluation; REST APIs; FastAPI or equivalent; PySpark; Delta Lake; Unity Catalog; responsible AI and safety controls; Git; CI/CD; Docker; Kubernetes; Terraform; Azure Key Vault; managed identities; monitoring and observability.
Experience and Qualifications
• 10+ years of software, data, analytics or machine-learning engineering experience, including leadership of complex AI workstreams.
• Proven experience designing and delivering production-grade AI assistants, conversational AI, RAG and agent-based solutions in enterprise environments.
• Strong hands-on experience with Azure, Databricks, Python, APIs, vector retrieval, evaluation and AI observability.
• Experience defining non-functional requirements for security, scalability, resilience, latency, cost and auditability.
• Experience leading distributed teams, stakeholder workshops, technical reviews and production readiness activities.
• Bachelor’s or master’s degree in Computer Science, AI, Data Science or a related discipline; Azure or Databricks certification is preferred.
Domain Experience
• Strong Insurance or employee-benefits experience across policy, plan, enrollment, eligibility, claims, renewal or advisory processes.
• Experience handling regulated, sensitive and health-adjacent information with traceable and human-governed AI outputs.
• Experience building document-grounded and data-grounded AI assistants for insurance or benefits use cases, including guided conversations, evidence-backed responses, human handoffs and governed actions, is advantageous.
Core Competencies
AI engineering leadership, hands-on technical depth, responsible AI ownership, evaluation discipline, structured problem-solving, stakeholder communication, mentoring and the ability to balance business value with grounding, safety, security, cost and maintainability.