Researcher and open source contributor working at the intersection of reinforcement learning and large language model inference.
I contribute to open source projects in the agent-based modeling and LLM tooling space, including Mesa and mesa-llm. My previous GitHub account was Nithin9585, where I first started contributing to open source.
- Researching reinforcement learning
- Exploring inference in large language models
- Open to research opportunities and collaborations in RL and LLMs
- Contributing bug fixes and improvements to Mesa , mesa-llm and google(tunix) an agent-based modeling framework in Python
- Interested in LLM-focused extensions of agent-based modeling, such as mesa-llm
- Email: nithin958595@gmail.com
- LinkedIn: nithin-nagaraj
- Discord: Join

