$ whoami
Prabhsurat Singh
Computer Science @ GGSIPU
ML • Reinforcement Learning • LLMs • Backend Systems
$ building
> Reinforcement Learning algorithms and benchmarks
> GPU Kernels
> LLM post-training (PPO / RLHF)
> Distributed backend systems
> AI developer tools
$ stack
Python | PyTorch | C++ | FastAPI | Docker
CUDA | Redis | Kafka | PostgreSQL
$ currently
Lead Engineer @ Heimatverse
Researching RL fine-tuning for compact LLMs
Playing around with CUDA and Robot Learning
$ status
Always building.
👻
meh. I code.
- New Delhi, India
-
12:01
(UTC +05:30) - in/prabhsurat-singh-1868052ab
- @NeonEdge05
- https://prabhsuratsingh.github.io
Highlights
- Pro
Pinned Loading
-
RL-From-Scratch
RL-From-Scratch PublicImplementation of various Reinforcement Learning algorithms and environments
Python
-
Atari-RL
Atari-RL PublicImplementation of Deep Q-Networks (DQN) for Atari 2600 environments using the Arcade Learning Environment (ALE) via Gymnasium.
Python
-
rl-robotics-simulations
rl-robotics-simulations PublicImplement Deep RL methods on MuJoCo environments, via command line interface
Python
-
Proteios-Mini
Proteios-Mini PublicProteios is an innovative platform designed to simplify and enhance protein research and drug discovery. It integrates cutting-edge Google AI and ML technologies to provide efficient protein analys…
-
-
Something went wrong, please refresh the page to try again.
If the problem persists, check the GitHub status page or contact support.
If the problem persists, check the GitHub status page or contact support.


