Skip to content
View saranshagarwal202's full-sized avatar
1 follower · 0 following

Achievements

Achievement: Pull Shark

Achievements

Achievement: Pull Shark

Block or report saranshagarwal202

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Maximum 250 characters. Please don’t include any personal information such as legal names or email addresses. Markdown is supported. This note will only be visible to you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
saranshagarwal202/README.md

Hey, I'm Saransh 👋

New Grad SWE | Backend & ML Systems | MS Data Science @ Texas A&M
📍 United States • Actively looking for opportunities

AWS Solutions Architect Professional

💼 What I've Built

Research @ Texas A&M — Distributed LLM training pipelines (DeepSpeed, SLURM), reduced multimodal inference latency by 21%, built scalable benchmarking frameworks.

@ Viewzen Labs (2 yrs) — Architected an MLaaS platform handling 80+ concurrent training jobs, built data pipelines processing 5M+ daily events with Kafka & Docker, shipped a production prediction system.

📄 Publications

  • [SemEval-2025] Constrained Unlearning for LLMs — 🥈 2nd Place, Task 4
  • [EACL 2026] Adaptive Helpfulness-Harmlessness Alignment with Preference Vectors

🛠 Stack

Python Rust Go C++ PyTorch Docker Kubernetes AWS

📫 Let's Talk

LinkedIn Email Website

Open to Backend, ML Infra, and Platform Engineering roles.

Pinned Loading

  1. lab-flair/Constrained-Unlearning-for-LLM lab-flair/Constrained-Unlearning-for-LLM Public

    Python 3

  2. distributed_mmlu_benchmarking distributed_mmlu_benchmarking Public

    Python

  3. Satellite_based_crop_monitoring_system Satellite_based_crop_monitoring_system Public

    JavaScript

  4. NVIDIA/kvpress NVIDIA/kvpress Public

    LLM KV cache compression made easy

    Python 1k 135