• Backend Leadership: Lead several challenging large-scale projects backends to completion through planning and executing complex software architectures.• GenAI Architectures: Utilized and Customized multiple Generative AI Architectures such as ReAct, RAG, and more according to the business use case.• Vector Databases: Utilized multiple vector databases through creating custom hybrid search strategies to yield the best search results.• LLM Models: Created custom LLM interfacing services to decrease latency and increase efficiency.• Efficient Engineering: Delved into customizing networking, services, and more within backends to improve latencies in an unprecedented manner to produce real time responses.• LLM Scraping: Performed AI-Assisted token-efficient breadth and depth scraping to ingest data necessary for RAG generative AI flows.

- Actively engaged in creating diverse projects through developing clustered Java backend applications, intricate games, and simulated CPU schedulers.- Gained proficiency in utilizing the Spring Boot framework, deploying applications on Google Cloud Platform (GCP), implementing Docker containers, and scripting in Shell.