AI Engineering Lead

Key Responsibilities

• Build and Deliver AI Solutions
• Design, build, and deploy production-grade end-to-end AI solutions, including workflow automation agents, RAG pipelines, and copilots embedded in business workflows, and LLM-driven applications
• Translate business needs into technical designs and working products to deliver usable, high-impact solutions, not just proofs of concept
• Architect and implement AI-assisted data workflows and agentic systems
• Build and maintain LLM-enabled services, prompt frameworks, and coding standards
• Develop semantic/context layers ensuring AI outputs align with business logic and data models
• Design multi-agent workflows, including human-in-the-loop controls
• Make pragmatic tradeoffs to ship quickly while maintaining long-term sustainability
• Technical Design and Architecture
• Create scalable patterns for prompt design & orchestration, agent-based workflows, and API integrations & data access
• Inform architecture decisions for AI systems balancing speed, security, scalability, maintainability, and cost
• Help establish engineering standards and best practices for applied AI across the organization
• Evaluate and recommend tooling across the stack (models, frameworks, vector stores, orchestration layers)
• Define data requirements and, when needed, build or extend data pipelines to ensure AI systems have reliable, production-ready inputs
• Quality, Reliability, and Production Operations
• Design and implement evaluation frameworks to define and track AI system performance, including task success, accuracy, latency, cost, and business impact; establish feedback loops to continuously improve quality, reliability, and cost-efficacy in production environments
• Build guardrails and validation layers to reduce hallucinations, enforce structured outputs, and ensure safe system behavior
• Establish monitoring and observability across AI systems (performance, usage, cost, latency, failure modes)
• Implement modern engineering practices including CI/CD, versioning, rollback strategies, and automated testing
• Ensure solutions meet security, compliance, and governance requirements in a regulated environment
• Cross-Functional Delivery and Adoption
• Partner with business leaders, operations & service teams, and product stakeholders to shape use cases and turn them into working solutions
• Work closely with AI Enablement to refine workflows and improve adoption
• Drive fast iteration cycles, quickly moving from idea to working solution to scaled implementation; iterate solutions based on real user feedback and usage patterns

Required Qualifications

• 7-10+ years in software engineering, data engineering, or AI/LLM experience
• Hands-on experience building and deploying production AI systems
• Hands-on experience building applications using LLMs and modern AI tooling
• Experience with cloud platforms (Azure preferred), Python, APIs, containerization, and CI/CD practices
• Experience building RAG pipelines, agent-based workflows, or orchestration layers
• Experience with vector databases, embedding pipelines, and retrieval systems
• Strong problem-solving ability and bias toward practical, efficient solutions; ability to operate in a fast-moving, ambiguous environment
• Experience translating business needs into technical solutions

Preferred Qualifications

• Experience working in the Microsoft ecosystem
• Experience implementing evaluation frameworks, guardrails, and observability for AI systems
• Experience working in regulated industries (insurance, financial services, healthcare)
• Exposure to full-stack development (frontend + backend) for delivering usable AI experiences