Responsibility

• Design and implement evaluation pipelines for both closed and open-source Large and Small Language Models, capturing key metrics such as performance, latency, cost, hallucination, helpfulness, harmlessness, quantization, and fine-tuning
• Develop advanced Textual Information Retrieval, classification, and clustering algorithms using frameworks like SpaCy, NLTK, and Hugging Face
• Enable GenAI business use cases on Docusign infrastructure with a strong emphasis on security and governance
• Build autonomous and workflow-based agents for business applications using CrewAI or similar agentic frameworks, and support agentic AI platforms
• Drive world-class implementation of the no-code agentic platform Glean, developing custom agents to serve as AI assistants for employees
• Fine-tune GenAI models to optimize performance, scalability, and reliability
• Support buy vs. build evaluations for GenAI solutions
• Implement prompt engineering best practices to minimize token usage and improve output accuracy; contribute to a centralized prompt library
• Develop robust tools to automate RAG pipeline creation, integrating diverse datasets into vector databases and incorporating knowledge graphs as needed
• Help building conversational tools  to answer business questions from structured data systems ( analytical AI or QueryGPT) and applications like ChatGPT for the enterprise
• Conduct research to advance generative AI and apply findings to real-world use cases
• Document processes, models, and code to ensure maintainability and reproducibility
  • Collaborate with business teams to translate requirements into effective technical solutions