about

last updated january 2026

hey @everyone, swapnil here.

i’m a just a nerd who loves building things that look and feel great and or pique my interest in a particular topic.

this website is a living record of my work, projects, musings, curiosities and research. it will be updated as i progress in my journey. in the very near future, i will also use this site for collecting articles, videos and bookmarks.

currently interested in

• Embodied AI & VLA Architectures (language reasoning with robotic control in ROS 2)
• Geometric Computer Vision (6D Object Pose Estimation and 3D scene understanding)
• High-Performance ML Systems
• Cognitive Architectures for Agents (hybrid memory systems using Knowledge Graphs + Vector DBs)
• Declarative Infrastructure (reproducible builds and dev environments with Nix, pixi)
• Reinforcement Learning in agentic systems
• model architectures, pre-training and post-training of LLMs, inference optimizations, RLVR

currently working on

• an OpenEnv-compliant computer control environment where AI agents can learn to perform desktop tasks, using TRL (Transformers Reinforcement Learning) with GRPO
• training a small language model from scratch
• this website

not work

• In my free time, i hop on valorant and marvel rivals with my friends
• i also like to indulge in some digital art from time to time

contact

• you can reach me at swapnil@rycerz.es
• fairly active on discord @swappy._.