Senior AI / ML Research Engineer
Specializing in Reinforcement Learning, LLMs / VLMs / VLAMs, and Embodied / Physical AI
I am a senior applied AI/ML Engineer with 15 years of experience building intelligent agents through Reinforcement Learning, Multimodal Models, and Simulation. I've had the privilege of delivering production-grade solutions across industries ranging from aerospace and defense to robotics. My work spans Reinforcement Learning, physics-based Modeling and Simulation, and is now expanding into LLMs, VLMs, and VLAMs. I'm focused on combining embodied learning with RL and multimodal AI to tackle real-world challenges.
My passion is right at the intersection of AI, simulation, and decision-making. I focus on:
- 🧭 Reinforcement Learning (online/offline, adversarial, multi-agent)
- 🧠 LLM / VLM / VLAM Fine-Tuning & Alignment (SFT, DPO, RLHF/RLAIF)
- 🛰️ Embodied AI in high-fidelity simulators (Isaac Lab, Genesis)
I’m always happy to chat with people who share my interests and passions. Feel free to reach out!
- 🌐 Personal Website
- 🧠 Artificial Twin - The brand behind my AI/ML consultancy activity with the mission of building intelligent agents
Here are a few of my public repositories that reflect my work and interests:
| 🔀 Extending GPU-Native RSL-RL Library | 🛡️ RL Drone Swarm Defense | 🕹️ DIAMBRA Arena | 🤖 DIAMBRA Agents |
|---|---|---|---|
|
|
|
|
| Customized fork of RSL-RL library that supports multi-discrete action spaces. | Counter-kamikaze drone swarm with multi-agent reinforcement learning in a realistic simulation. | A platform to train reinforcement learning agents in classic retro fighting games. | A library of reinforcement learning algorithms tailored for DIAMBRA Arena environments. |
- Experimenting with adversarial RL for LLM alignment fine-tuning
- Exploring speculative decoding for fast LLM inference
- Learning Triton to optimize GPU workloads for small-scale LLMs
- Testing agentic frameworks for multi-step coordination
- Moving toward Vision-Language-Action models