Principal AI Engineer - Generative AI We're looking for a highly experienced and innovative Principal AI Engineer to drive the development and adoption of our LLM Platform and Generative AI initiatives. Innovation is at the core of this role — you will be expected to continuously push boundaries, experiment with emerging AI techniques, and translate cutting-edge research into production systems. You will architect scalable AI platforms, shape our engineering strategy, and provide expert guidance across cross-functional teams. In this role you will: Hands-on Development: Design, build, and test core LLM platform components, Generative AI agents, and supporting tooling in Java — ensuring production-grade quality, performance, and reliability. Architecture System Design: Lead the design and implementation of robust, scalable systems for LLM orchestration, RAG pipelines, agent workflows (Google ADK), fine-tuning, model serving, and API development on AWS. RAG Knowledge Systems: Architect and own Retrieval-Augmented Generation systems end-to-end — embedding pipelines, vector store selection and tuning, chunking strategies, retrieval evaluation, and integration with generative models. Agent Engineering: Build and evolve multi-agent systems using Google Agent Development Kit (ADK), defining patterns for tool use, memory, orchestration, and inter-agent communication. Innovation Research: Actively track and evaluate emerging Generative AI research, frameworks, and tools. Prototype novel ideas, run experiments, and champion the adoption of techniques that create competitive advantage. Performance Evaluation: Define evaluation metrics and conduct rigorous assessments of Generative AI and RAG solutions to ensure business impact and continuous improvement. Mentorship: Mentor and inspire junior and mid-level engineers — through code reviews, pairing sessions, design guidance, and deliberate investment in their growth. Foster a culture of curiosity, ownership, and continuous learning. Cross-Team Guidance: Serve as the subject matter expert for multiple teams building Generative AI features — content generation, code assistance, customer support automation, data augmentation, and more. You've Got What It Takes If You Have... 10+ years of software engineering experience with a strong focus on AI/ML systems, including 3+ years hands-on with LLMs and Generative AI in production. Deep expertise in Retrieval-Augmented Generation (RAG) — including vector databases, embedding models, hybrid search, and evaluation frameworks. Proven track record designing and shipping complex, high-scale AI systems on AWS (SageMaker, Bedrock, Lambda, ECS, etc.); GCP experience a plus. Strong Java engineering skills; experience building production AI services and APIs in the JVM ecosystem. Hands-on experience with Google Agent Development Kit (ADK) or comparable agentic frameworks (LangGraph, LangChain, etc.). Demonstrated passion for innovation — a track record of introducing new ideas, not just executing on existing ones. Experience mentoring engineers at various levels and contributing to team capability growth. Solid understanding of data governance, privacy, and responsible AI principles as applied to LLM systems. Excellent communication skills — able to translate complex AI/engineering concepts for both technical and non-technical stakeholders. #LI-Onsite