Gen AI Engineer

As a Lead AI Engineer, you will be responsible for designing, architecting, and leading the development of advanced AI systems that combine data pipelines, Retrieval-Augmented Generation (RAG), Knowledge Graphs, and intelligent agent orchestration. You will play a critical role in building scalable, reliable, and secure AI infrastructure, while guiding a team of engineers and collaborating with cross-functional stakeholders. Key Responsibilities: Data & Feature Pipelines: Design, build, and maintain robust data ingestion and feature-store pipelines supporting both traditional ML models and Large Language Model (LLM) applications. Ensure pipelines meet scalability, latency, and reliability requirements. Retrieval-Augmented Generation (RAG): Architect and implement RAG systems: build vector stores, define embedding strategies, integrate semantic search over document corpora, and optimize for low-latency, high-relevance retrieval. Continuously evaluate and tune retrieval pipelines for performance and cost efficiency. Knowledge Graphs: Model and construct enterprise Knowledge Graphs (KGs): define ontologies, entity schemas, relation types, and ingestion pipelines (e.g., Neo4j, Cosmos etc). Develop graph-based inference and reasoning capabilities to enrich data pipelines and ground generative AI outputs in verified knowledge. Collaborate with data architects to align KGs with enterprise data warehouses, metadata catalogs, and governance frameworks. AI Agents & Orchestration: Architect and implement goal-driven AI agents capable of multi-step planning and execution, including error handling and adaptive task re-sequencing. Integrate and extend orchestration frameworks (e.g., Microsoft AutoGen, LangChain Agents, custom schedulers) to manage workflows, tool-use, and state persistence. Establish secure, auditable agent pipelines with governance controls, logging, and human-in-the-loop checkpoints. Deployment & MLOps: Lead containerization and deployment of ML, RAG, KG, and agentic components using Kubernetes or serverless platforms. Build and enforce CI/CD pipelines for models and AI components, ensuring safe and automated rollouts. Implement monitoring for model drift, retrieval accuracy, graph consistency, and agent performance, tied to SLAs/SLIs. Define and automate rollback, alerting, and canary release strategies to minimize operational risk. Leadership & Innovation: Stay current with cutting-edge research in RAG architectures, graph neural networks, autonomous agents, and orchestration tooling. Mentor and guide junior engineers in AI/ML best practices, scalable system design, and operational excellence. Collaborate with product and business teams to translate high-level objectives into executable AI solutions that deliver measurable impact.