Feature Engineering Pipeline: Design, build and maintain reliable feature engineering pipelines on Databricks and AWS for ingesting, transforming, validating and serving structured and unstructured data used by ML/AI workloads.
Agentic AI Architecture: Design the end-to-end architecture for FAM agentic AI solutions, including agent orchestration, workflow design, state management, tool integration, human approval points and system interactions, using suitable frameworks such as LangGraph or CrewAI. Architecture decisions are subject to consultation with DSAD’s Platform Team.
Performance Evaluation & R&D Reporting: Design rigorous testing environments to validate model accuracy. Present technical bottlenecks, algorithmic optimizations, and milestone results in regular R&D reviews with your supervising Director
Implement task planning, dialogue management, intent recognition, tool invocation, process engineering, RAG, etc. for intelligent agents based on LangChain, LangGraph, LlamaIndex, and Agent Framework.
Synthetic Data Methodology : Design physics-constrained generative model approaches (diffusion models, VAEs) for synthetic data generation. Deliver validated methodology and training recipes for pipeline operationalization.