Experience

DoorDash — Software Engineer

2025 – present · New York, NY

Building ML-powered systems and platform infrastructure.

PineGap.ai — ML Engineer Intern

May 2024 – Aug 2024

First AI hire. Owned and built everything from scratch.

• Designed end-to-end components of a keyword-guided retrieval and search engine using BM25, Elasticsearch, dense vector search, fine-tuned Splade, and ColBERT models for query augmentation and candidate reranking.
• Built an advanced agentic RAG framework with CI/CD pipelines for query understanding, document ingestion, and knowledge graph building — supporting Q&A over 10 years of financial documents from S&P 2000 companies.
• Containerized microservices to fine-tune and serve LLMs (LLaMA-3, Phi-3, Mixtral) as APIs using Docker and Kubernetes. Employed quantization, flash attention, LoRA, data and model parallelism, vLLM, paged attention, Kafka, and Redis for efficient inference.

Instabase — Software Engineer, Machine Learning

Jan 2022 – Aug 2023

• Integrated LLMs, RAG, and Generative AI capabilities into Instabase’s Document AI platform, including model inference service, regression, and load-testing framework.
• Designed and implemented an async model serving platform using async workers, RabbitMQ, multi-level caching, sticky routing, and hardware acceleration (ONNX + model pruning) — reduced inference time by 40% in a compute-limited Kubernetes environment.
• Enhanced OCR service using LayoutLM for better table extraction (+60%). Developed an algorithm to detect and process vertical text in PDFs.
• Built a pipeline to detect format and content drift in production documents.

Walmart Global Tech India — Software Engineer II

Aug 2020 – Dec 2021

• Implemented entity embeddings for sparse categorical values — improved forecasting accuracy by 17% and reduced inference time by 15%, while minimizing manual feature engineering.
• Enhanced gradient boosting to incorporate distribution center manager feedback. Implemented weighted loss to penalize misclassification of perishable items more heavily.

Google Summer of Code — AOSSIE

May 2019 – Aug 2019

• Developed a Chrome extension using NLP to detect toxic comments, clickbait, and fake news on Facebook, Twitter, and news sites in real time.
• Trained a stance detection model for fake news classification with a Flask inference backend.
• Designed a three-level cache system to minimize latency and avoid duplicate requests.

Genesys — Applied Research Intern

May 2019 – Jul 2019

• Implemented a passage ranking algorithm to improve accuracy of in-house Q&A services on client datasets.
• Built a framework to train AllenNLP machine reading comprehension models on medical data for a client POC and proposed integration with the homegrown chatbot.

Education

New York University - Courant Institute Of Mathematical Sciences

Master of Science, Computer Science [AI specialization]

Sep 2023 - May 2025

Subjects: Deep Learning, Large Language and Vision Models, Deep Reinforcement Learning, Computer Vision, Conceptual Gaps in Modern Machine Learning, Cloud and Machine Learning, Operating Systems, Programming Languages, Algorithms.

Indian Institute Of Technology (ISM), Dhanbad

Bachelor of Technology, Computer Science and Engineering

July 2016 - April 2020

Major Subjects: Data Structures, Algorithms, Object Oriented Programming, Operating Systems, Database Management and Systems, Distributed Systems, Discrete Mathematics, Calculus.