Daksh Jain

Python, C++, PyTorch, LangChain, Gymnasium, Gradio. Specialized in ML/RL & Agentic AI, but capable of full-stack UI/UX styling (Bento grids/glassmorphism) for modern SaaS apps.

Exploring Multi-Agent Reinforcement Learning (MAPPO), scaling Agentic AI architectures, and optimizing LLMs for production. Constantly sharpening my CP algorithms as a CF Specialist.

Building a 12-part Reinforcement Learning portfolio with custom Gym environments. Also developing Commando AI (agentic workflow automation) and Parallax (DevSecOps guardian).

Discussing RL environments, multi-agent AI, and CP algorithms. Open to collaborating on hackathons and connecting about SDE/ML internship opportunities for Summer 2027.