Software Engineer @ NYU IT | MS CS @ NYU | Gen AI, Distributed Systems, AWS, Python, Java | Ex-Shell, Wipro
Software Engineer with 3+ years of experience bridging the gap between research-level Generative AI and Production Infrastructure. Having prior experience in Energy, Bioinformatics, and Scientific research domains.
Provided technical mentorship and primary support to 50+ graduate students via office hours and Ed Discussions, ensuring engagement and clarity on complex ML topics.
โข
Collaborated with faculty to design assignments on real-world ML workflows, including data preprocessing pipelines and model evaluation metrics.
โข
Wrote Python scripts to automate grading of Jupyter notebooks, reducing feedback turnaround time by 40%.
๐๐๐๐ถ๐ป๐ฒ๐๐ ๐ฃ๐ฟ๐ผ๐ฏ๐น๐ฒ๐บ: NYU Research Department struggled to identify collaborators due to siloed data across disparate systems, stalling interdisciplinary discovery to invest in potential research labs across the world.
Architected a Research Discovery Engine using LangGraph and Llama 3.1 70B to map global researcher collaborations by indexing massive datasets from Elsevier (ScienceDirect/Scopus).
โข
Implemented a Multi-Agent โSearch Routerโ to handle hybrid semantic queries across scientific nomenclature; utilized BGE-M3 and Reciprocal Rank Fusion (RRF) to improve keyword matching accuracy by 40%.
โข
Engineered a hybrid cloud processing pipeline using Node.js and FastAPI on AWS ECS, scaling asynchronous workers to sustain 99.9% uptime under peak loads of 3K+ requests per second.
โข
Optimized Retrieval Performance by deploying a Write-Through Redis cache, slashing P99 latency for complex โChain of Retrievalโ lookups from 450ms to <100ms.
โข
Led Full-Stack Ownership of the application lifecycle, designing the CI/CD strategy over Kubernetes and persistent volumes to reduce deployment lead times by 65%.
๐๐๐๐ถ๐ป๐ฒ๐๐ ๐ฃ๐ฟ๐ผ๐ฏ๐น๐ฒ๐บ: Federation of research data from external sources (like Elsevier Scopus, Science Direct) was slow and unreliable, leading to high latency for end-users.
๐๐ป๐ด๐ถ๐ป๐ฒ๐ฒ๐ฟ๐ถ๐ป๐ด ๐ฆ๐ผ๐น๐๐๐ถ๐ผ๐ป: Engineered a High-Concurrency Distributed Search Engine.
โข
Built a FastAPI microservice on AWS ECS (Fargate) utilizing AsyncIO to parallelize data fetching from 5+ external APIs, slashing P99 latency from 450ms to <100ms.
โข
Deployed a Redis Write-Through caching layer with custom TTL eviction policies, handling >300 RPS with sub-millisecond retrieval times.
โข
Modernized CI/CD pipelines using Docker and Kubernetes, enabling zero-downtime blue-green deployments.