Aug 2025 – Present · 10 mos

Apr 2023 – Aug 2025 · 2 yrs 4 mos

• Developed and deployed AI/ML models as solutions, implementing distributed architectures for scalability.
• Built a in house translation application with 400+ users using open-source Hugging Face models and fine-tuning using the Zephyr model.
• Utilized Judge LLM to define benchmarking logic for evaluating and comparing various Large Language Models (LLMs).
• Developed an end-to-end chat application enabling users to converse about document content: Employed a Retrieval-Augmented Generation (RAG) architecture to query PDF documents using Llama and a reranker model, leveraging a vector database for efficient retrieval.
• Managed the deployment of NLP applications on AWS using Jenkins pipelines.

Oct 2021 – Apr 2023 · 1 yr 6 mos

• Develop and manage data infrastructure and pipelines: This includes using AWS services, Python libraries, and data processing tools to build and maintain data pipelines.
• Design and implement data transformations: This involves analyzing requirements, designing ETL processes using Talend, and creating data visualizations in Tableau to support data-driven decision making.
• Collaborate across teams: This includes working with various teams to ensure successful data management and communication.