Summary: The Lead AI Engineer will standardize GenAI agent development, validation, and deployment, developing platform features, improving controls, and mentoring engineers. Highlights: 1. Lead initiatives to standardize GenAI agent development and deployment 2. Develop full-stack applications, AI agents, and platform components 3. Mentor engineers and steer architectural decisions for large-scale projects We are creating a shared GenAI Platform, and a Lead AI Engineer will help standardize how teams build, validate, and deploy AI agents at scale. You will develop platform features and agent workflows, improve evaluation and rollout controls, and mentor engineers while owning major initiatives—apply now. **Responsibilities** * Build and evolve full\-stack applications, AI agents, and platform components that accelerate GenAI agent development, validation, and deployment * Deliver developer tools, CI/CD pipelines, and observability capabilities for safe iteration, including evaluation systems, canary releases, rollout/rollback mechanisms, and cost and quality monitoring * Implement secure software development lifecycle (SDLC) and privacy\-by\-design controls, including threat modeling and least privilege access * Coordinate with product managers, UX designers, and domain experts to deliver customer\-focused solutions with measurable results * Use established LLM patterns, including retrieval\-augmented generation (RAG), retrieval, routing, tool\-use, and evaluation strategies, to increase reliability and speed, reduce time\-to\-decision, strengthen trust and safety, and lower cost per query * Mentor engineers and steer architecture decisions while taking ownership of large\-scale projects **Requirements** * Minimum 5 years of professional software engineering experience * At least 1 year of experience leading and managing development teams * Demonstrated capability to deliver software products solo or as part of a small, agile team * Experience delivering AI agents from concept through production, including safety assessments, iterative testing such as A/B testing, and continuous optimization * Hands\-on experience with LangChain or LangGraph, MCP, vector databases or RAG systems, and OpenSearch * Background in classic machine learning work, including model training, deployment, and monitoring * Familiarity with compliance and regulatory standards such as SOC2 and HIPAA * Excellent problem\-solving skills, strong ownership, and effective cross\-functional communication * Advanced full\-stack development ability and exposure to cloud platforms like AWS, Azure, or GCP * Proficiency with CI/CD practices and Infrastructure as Code * Knowledge of Site Reliability Engineering (SRE) principles * Experience with quality engineering and testing strategies * Understanding of secure SDLC and privacy by design principles * Proficiency in TypeScript * Fluent English communication skills, both written and spoken, at B2\+ level or above **Nice to have** * Knowledge of how large language models (LLMs) operate, including known failure modes * Exposure to fine\-tuning and model adaptation methods