Work Experience
Machine Learning Engineering Intern
Narada AI · Berkeley, CA · June 2025 – Present
  • Used off-policy distillation on local LLMs for 45–50% improved agentic performance.
  • Utilized GEPA to push our web agent to state-of-the-art performance on WebArena by over 10%.
  • Created the entire agent evaluation pipeline used to benchmark our web agent's performance.
Machine Learning Research Intern
Berkeley AI Research (BAIR) · Berkeley, CA · Nov 2025 – March 2026
  • Engineered distributed training infrastructure for multi-billion parameter early-fusion models on NVIDIA H200 clusters using PyTorch FSDP and optimized multiprocessing.
  • Architected multi-million example datasets from raw video data to train and fine-tune world models.
Machine Learning Research Intern
NASA Ames Research Center · Moffett Field, CA · May 2024 – Aug 2025
  • Implemented efficient pipelines to train ensembled models across multiple cross-validation splits in PyTorch, classifying objects across 100GB+ of stellar light curve data.
  • Developed robust training infrastructure implementing FGSM and PGD attacks; improved model reliability from 50% to 90% while maintaining zero accuracy regression.
  • Engineered an adversarial benchmarking suite and integrated robustness evaluation into the ML production pipeline to automate large-scale experiment tracking.

© 2026 Adithya Giri. All Rights Reserved