Generative AI Development Design and implement enterprise GenAI applications using LLMs. Develop multi-agent workflows and agentic AI systems using LangGraph. Build conversational AI, copilots, knowledge assistants, and intelligent automation solutions. Engineer prompts and workflows to optimize model performance and user experience. RAG & Knowledge Systems Design and implement Retrieval-Augmented Generation (RAG) pipelines. Integrate vector databases and document retrieval frameworks. Optimize document chunking, embeddings, indexing, retrieval, and reranking strategies. Improve response accuracy, latency, and relevance of AI systems.
Additional Responsibilities:
Deployment & Productionization Deploy and serve models using MLflow and Databricks. Monitor model performance, drift, and operational metrics. Implement CI/CD pipelines for AI and machine learning workloads. Ensure scalability, reliability, and observability of AI services. Leadership & Mentorship Mentor junior engineers and AI practitioners. Conduct design reviews and architecture discussions. Define GenAI development standards and best practices. Collaborate with business stakeholders to identify AI use cases and translate them into solutions.
Technical and Professional Requirements:
AI Platform Engineering Build scalable AI platforms on Databricks and cloud environments. Develop model lifecycle management solutions using MLflow. Implement model tracking, versioning, deployment, monitoring, and governance. Support MLOps and LLMOps initiatives. Data Engineering Build and optimize large-scale data pipelines using PySpark. Process structured and unstructured data for AI and analytics workloads. Collaborate with data engineering teams to build feature and knowledge pipelines. Ensure data quality, lineage, and governance standards.
