KAMAL RAJ

Developed an Auto-ML tool within a Low Code/No Code SaaS platform using the Vaex library. Employed Bayesian optimization techniques to fine-tune hyperparameters for both classification and regression supervised machine learning models. Designed, developed, and tested API endpoints for the Mobius Low code/No code platform using FastAPI. Developed and deployed a production-ready SQL query generation code using SQLAlchemy, Langchain, and OpenAI GPT-4. Leveraged Hugging Face’s open-source large language models Llama 7B and nSQL-6B to automate the generation of SQL queries. Developed a vectorDB faiss-based prototype for a question-answering system that can search and answer questions from multiple PDF documents. Implemented code generation through Langchain by transferring the output from one Language Model to another Language Model. Documented all research activities. Applied Bayesian optimization techniques for hyperparameter tuning in ML models. Utilized prompt templates and Langchain Agents to build projects.

Analyzed engineering problems/issues, proposed and implemented effective solutions. Validated designs through hand calculations/prototypes to support engineering decisions. Contributed to the expansion of the PECVD VECTOR® DT product range for backside deposition in 3D NAND manufacturing as a cost-effective solution for controlling wafer bow. Provided effective and fast solutions for problem report’s from customers and issue log’s from manufacturing. Given multiple design reviews from preliminary to final design phases.