Summary: Lead AI Engineer to architect, deliver, and operationalize scalable GenAI agents end-to-end, establishing robust pipelines and guiding architectural choices. Highlights: 1. Architect and deliver full-stack applications and AI agents 2. Drive hands-on leadership through architecture and mentoring 3. Apply modern LLM patterns to improve speed and reliability We are expanding our GenAI Platform and looking for a Lead AI Engineer to power scalable agent development, testing, and production rollout for many teams. You will deliver AI agents end to end, establish robust pipelines and guardrails, and guide engineers through key architecture choices—apply today. **Responsibilities** * Architect and deliver full\-stack applications, AI agents, and platform components that enable rapid GenAI agent development, validation, and deployment * Build developer tooling, CI/CD pipelines, and observability capabilities to support safe iteration, including evaluation systems, canary releases, rollout/rollback mechanisms, and cost and quality monitoring * Enforce secure software development lifecycle (SDLC) and privacy\-by\-design practices, including threat modeling and least privilege access * Partner with product managers, UX designers, and domain experts to ship customer\-focused solutions with measurable outcomes * Apply modern LLM patterns, including retrieval\-augmented generation (RAG), retrieval, routing, tool\-use, and evaluation strategies, to improve speed and reliability, reduce time\-to\-decision, increase trust and safety, and lower cost per query * Drive hands\-on leadership through architecture decisions, engineer mentoring, and ownership of large\-scale projects **Requirements** * At least 5 years of professional experience in software engineering * Minimum 1 year of experience leading and managing development teams * Proven ability to deliver software products independently or within a small, agile team * Experience bringing AI agents from idea to production, including safety reviews, iterative testing such as A/B testing, and continuous improvement * Hands\-on expertise with LangChain or LangGraph, MCP, vector databases or RAG systems, and OpenSearch * Solid background in traditional machine learning tasks, including model training, deployment, and monitoring * Working knowledge of regulatory standards such as SOC2 and HIPAA * Excellent problem\-solving ability, strong ownership mindset, and effective cross\-functional communication * Advanced full\-stack development skills and experience with cloud platforms like AWS, Azure, or GCP * Hands\-on proficiency with CI/CD practices and Infrastructure as Code * Good understanding of Site Reliability Engineering (SRE) principles * Experience applying quality engineering and testing strategies * Clear understanding of secure SDLC and privacy by design * Strong proficiency in TypeScript * Fluent English communication skills, both written and spoken, at B2\+ level or above **Nice to have** * Understanding of large language models (LLMs), including typical failure modes and limitations * Experience using fine\-tuning and model adaptation approaches