Vibeleaderboard
← Back to Vibers
Manthan Gupta
Builder

Manthan Gupta

@manthanguptaa

2 Tools · 1 Intel

Manthan Gupta is an AI research engineer based in Bangalore, India, focused on the infrastructure powering modern AI — inference engineering, GPU kernels, and distributed training. He works as an independent AI engineer consultant and builds across agents, LLMs, and distributed systems, guided by a philosophy of "build to understand, write to clarify."

Is this you? Sign in with X to claim this profile.

Tools

Water(https://github.com/manthanguptaa/water)

Python framework for building multi-agent workflows with first-class observability.

AI AgentsOpen SourceFrameworks★ 337Apache-2.0built by manthanguptaa
Auto-Inference-Optimiser(github.com/manthanguptaa/auto-inference-optimiser)

Autonomous agent that hill-climbs LLM inference speed on Apple Silicon, tracking overnight experiments in git commits.

AI AgentsOpen SourceResearch Agents★ 38built by manthanguptaa

Intel

What Happened When I Applied Karpathy's Autoresearch Idea to LLM Inference(x.com)

Applying Karpathy's autoresearch idea to inference optimisation, and showing the graveyard of failed settings behind the headline speedup, including the ones that improved throughput by quietly degrading the model.

AI AgentsFreebuilt by @manthanguptaa