I'm a Computer Science Junior from Florida International University and passionate about Applied Deep Learning research and Software Engineering. I love to make an impact in my community and inspire curious people to do the same. Trying to make the world more sci-fi <3. I've previously worked at NVIDIA as an intern, and now partake in full-time research associated with LLMs, Robotics and self-study diffusion models (+ All the math behind these things).
- 🌱 I’m currently learning: JAX (see my Gists), CUDA, the XLA API, and Automatic Differentiation
- 🍓 Working on a StyleGAN project for real-time video generation
- GPT-2 (124M) From Scratch - Trained on 10% of OpenWebText sharded on 8 A100s using JAX. Optimized for KV-Caching, achieving linear token/s performance. (+ Bonus: Applied Pallas attention kernels to boost performance)
- Variational Auto-Encoders for MNIST → See my lecture! (Starts at 18:54) - Implemented in Flax & Optax to reconstruct smooth interpolations of a latent space trained on MNIST representations.
- NNs in JAX - RNNs, CNNs, LSTMs, and MLPs implemented in Flax.
- Tensor Autograd - Auto-differentiation engine in Python for PyTorch-like Tensor API for SGD optimization in computational graphs and neural networks. Includes backward methods for backpropagation in reverse mode AD.
- Vector-Jacobian / Jacobian-Vector Products - A thorough walkthrough of reverse and forward-mode AD with JVPs and VJPs. Visualized on a simple linear regression (very nice charts :D)
- Google - Software Engineering Intern (Incoming Summer 2025)
- NLP and ML Engineering for YouTube's Text Abuse team.
- DARPA - Undergraduate Researcher (September 2024 - Present)
- NVIDIA - Software Engineering Intern (Summer 2024)
- Worked on scaling the usability of a cloud infrastructure platform to orchestrate Machine Learning and Robotics workflows.
- Collaborated on the OSMO platform, using tools like Jenkins, ArgoCD, FastAPI, Next.js, and Bazel.
- Assisted in GEAR (Generalist Embodied Agents Research) Lab's research in Foundational Videogame Agents.
- INIT FIU - AI Lead & Director of Technology (Jan 2024 - Present)
- Taught weekly workshops on Machine Learning and Mathematics for a community of 35+ developers
- Collectively read and implemented multiple research papers as part of weekly projects.
- Collaborated to create the website to orchestrate ShellHacks 2024, with over 1,400 expected hackers.
- Google - Tech Exchange Student (Jan 2024 - May 2024)
- Participated in an exclusive educational program led by Google engineers and full-time employees.
- Selected as 1 of 3 out of 182 students to be a student speaker at the graduation cerimony for the program.
- Acquired applied computer science skills such as full-stack development, algorithms and data structures.
My main reserach interests are in:
- Mechanistic Interpretability of LLMs
- Code Generation
- Natural Language Processing
- Embodied AI
- Explainability in AI for Robustness in Autonomous Control Systems (NCUR 2024), Advised by Dr. Sumit Kumar Jha