resume

Education
Carnegie Mellon University Expected Dec 2026
Master of Science in Machine Learning Pittsburgh, PA
Anna University, College of Engineering, Guindy June 2022
B.E. (Honors) in Computer Science & Engineering Chennai, India
Work Experience
Google Jul 2022 – Jul 2025
Software Engineer (SWE II → SWE III) Hyderabad, India
  • Primary contributor to the risk strategy for Google Wallet via PIX in Brazil, launched August 2024. Developed risk mitigation solutions to reduce transaction losses across peer-to-peer payment flows.
  • Designed and deployed feature engineering pipelines in Java and rule-based decision policies in Python, integrating ML model outputs for real-time transaction risk assessment at scale.
  • Implemented regulation-compliant risk capabilities including real-time monitoring dashboards and operational runbooks. Collaborated with Trust & Safety and Product teams on metrics, thresholds, and customer impact post-launch.
  • Engineered ML pipelines for delinquency fraud detection on Stored Value transactions — data simulation, GBDT model training in TensorFlow, and offline evaluation against baselines.
  • Promoted from SWE II to SWE III (November 2024) for high-impact contributions to the Global Payments Platform Risk systems.
Goldman Sachs Jun 2021 – Jul 2021
Summer Analyst Remote (Bengaluru, India)
  • Created a Python-based data curation and analysis tool converting JSON inputs into multiple outputs for GS proprietary systems. Integrated into ETL workflows, optimizing a 2-week process to under one minute.
Research Experience
Forge Lab (Prof. Virginia Smith), Carnegie Mellon University May 2026 – Present
Graduate Student Researcher Pittsburgh, PA
  • Researching AI safety interventions for large language models, focusing on persona representations and behavioural drift in multi-turn conversations.
  • Studying inference-time and post-training interventions for improving model robustness, refusal behavior, and recovery from unsafe conversational trajectories.
  • Contributing to Safety Nudges, a real-time chatbot intervention tool for risks including overconfidence, sycophancy and unsafe responses.
Human Sensing Lab, Carnegie Mellon University Oct 2025 – May 2026
Graduate Student Researcher Pittsburgh, PA
  • Working on efficient 3D spatial understanding with 2D Vision-Language Models under Prof. Fernando De la Torre, Robotics Institute, in collaboration with Meta Reality Labs.
  • Developed diversity and coverage-aware visual token pruning methods for multi-view 3D visual question answering, achieving 60% faster inference, 88% fewer FLOPs, and 86% lower KV cache usage while maintaining comparable accuracy on 3D VQA benchmarks.
Indian Institute of Technology (IIT), Kharagpur May 2022 – Sep 2022
Deep Learning Intern Remote (Kharagpur, India)
  • Trained and evaluated semantic segmentation models in PyTorch for depth estimation from simulated colonoscopy images (KLIV group). Assessed various loss functions and post-processing techniques. Presented at the MICCAI 2022 Endoscopic Vision Challenge.
Projects
Watch & Learn: Teacher-Student Distillation for Robotic Arm Tasks Nov 2025 – Dec 2025
  • Developed a vision-only student agent from distillation of a full-state teacher policy for camera-based robotic manipulation on MetaWorld tasks. Achieved 90% of full-state teacher performance via teacher-guided RL with imitation learning.
Environmental ML: Modelling Sequential Disaster Cascades Jan 2026 – Present
  • Implemented an end-to-end ML pipeline on 15 years of NOAA Storm data for multi-hazard disaster chain prediction using MLPs with weather embeddings and GNN architectures with physics-informed features for rare event detection.
Adaptive Day Planner: LLM-Based Task Scheduling and Voice Agent Feb 2026
  • Built an AI-powered adaptive planner using Mistral LLMs, FastAPI and Eleven Labs speech APIs to dynamically schedule tasks, replan sessions based on user feedback and support focus sessions via conversational body doubling. (Mistral AI Worldwide Hackathon, SF)
Publications
SimCol3D - 3D reconstruction during colonoscopy challenge, A. Rau, S. Bano, Y. Jin, Varshini Elangovan, et al. Medical Image Analysis, 2024. doi: 10.1016/j.media.2024.103195
Reverse Image Search Engine for Garment Industry, Anushri Eswaran and Varshini E. 8th International Conference on Advanced Computing and Communication Systems (ICACCS), 2022. doi: 10.1109/ICACCS54159.2022.9785089
Courses
BlueDot Impact Issued May 2026
Technical AI Safety Course
Skills
Languages Python, Java, C/C++, SQL, JavaScript Frameworks / Libraries PyTorch, TensorFlow, Keras, NumPy, Pandas, scikit-learn, Hugging Face, OpenCV, OpenAI Gymnasium Developer Tools Git, Docker, Weights & Biases, FastAPI