Kaushik Shetti Email & Phone Number

India

Part of the Generative AI Platform team.• Formed a versatile RAG (Retrieval Augmented Generation) pattern migrating from text based search to semantic hybrid search.• Used Azure Cognitive Search and OpenAI's GPT-3.5 and GPT-4 models to perform semantic hybrid search on text based and vector based indexes.• Created an endpoint that specifically converted standalone question to VectorEmbeddings using EmbedQuery functionality from LangChain.• Consumed the vector embedding that came as a response from the API built to perform Hybrid Search which improved the response time by 30% as compared to text based search.• Made GPT model as a customizable property for end users to have a choice of the model from which they want answers.• Collaborated with Microsoft Azure team and implemented translation feature on the data coming after summarization from LLM models.• Built a system API endpoint that translated word document from English to a user's choice of desired language using Azure Machine Learning's Helsinki models while preserving the formatting of the original document in the converted translated document.• Partnered with the internal team for developing BYOD feature (Bring your own document) feature with the help of DIS (Document Intelligence Service) and Azure blob storage as a data source.

• Managed Amazon Web Services including EC2, S3 bucket, RDS, and AMI through the AWS Console.• Built CI/CD pipelines for applications using Github Actions.• Set up Virtual Private Clouds with subnets.• Configured AWS Identity & Access Management (IAM) by managing user accounts, roles, and groups.

• Developed RESTful APIs using Node.js and ORM tools such as TypeORM and Prisma.• Proficient in deploying web applications on SaaS platforms like Heroku and Netlify using CLI.• Experience with backend frameworks like Nest.js and Express.js.• Strong understanding of API design principles and best practices.

• Gained understanding of the fundamentals of machine learning and its various algorithms.• Applied image recognition and classification techniques to accurately determine the content.• Collaborated with the team to implement and optimize machine learning models.