This hands-on workshop dives deep into NVIDIA Nemotron™ 3 Super, a powerful 120B open hybrid Mamba-Transformer Mixture-of-Experts (MoE) model built for complex reasoning, long-context analysis, and autonomous problem-solving. You will explore key architectural innovations like Latent MoE and Multi-Token Prediction, and learn how to build, optimize, and deploy real-world AI systems using NVIDIA’s open weights, datasets, and deployment recipes.
WHO SHOULD ATTEND
AI/ML Engineers & Researchers: Professionals building advanced LLMs and specialized reasoning models.
Generative AI Developers: Developers creating complex, multi-agent AI applications (such as software development or cybersecurity triaging agents).
Data Scientists: Practitioners interested in state-of-the-art training techniques like Native NVFP4 pretraining and multi-environment reinforcement learning (RL).
DevOps & MLOps Engineers: Professionals looking to deploy high-throughput, low-latency AI models using vLLM, SGLang, or NVIDIA TensorRT-LLM.
AGENDA 10:00 AM – 10:30 AM: NVIDIA Nemotron strategy – open datasets, weights, frameworks, and recipes 10:30 AM – 11:00 AM: Deep dive into Nemotron 3 Super architecture design 11:00 AM – 12:15 PM: Efficient serving and deployment using vLLM, SGLang, and TensorRT-LLM Cookbooks 12:15 AM – 1:30 PM: Building agentic workflows using Nemotron models 1:30 PM - 2:15 PM - Lunch 2:15 PM - 2:35 PM - Talk by NVIDIA Partner - Amol Bhore, MD & CEO at Skymeric Technologies 2:35 PM - 2:55 PM - Talk by NVIDIA Partner - Rohit Anurag, Principal Data Scientist at Partex AI 2:55 PM - 3:10 PM - "Can Nemotron Understand Geometry?" by Yogesh Kulkarni 3:10 PM - 3:25 PM - "AI-Powered Network Attack Detection using NVIDIA Nemotron" by Sanket Sonwane 3:30 PM - Closing note by Coditas
KEY LEARNINGS
By the end of the workshop, attendees will be able to:
Understand Advanced Architectures: Grasp the mechanics behind the Hybrid Mamba-Transformer backbone, Latent MoE (which calls 4x as many experts for the same compute cost), and Multi-Token Prediction (MTP) for built-in speculative decoding.
Navigate the Training Pipeline: Understand how the model achieves stability and accuracy through Native NVFP4 pretraining and trajectory-based reinforcement learning across diverse environments (using NeMo Gym and NeMo RL).
Implement the "Super + Nano" Pattern: Learn how to architect multi-agent workflows that smartly route simple tasks to Nemotron 3 Nano and complex planning/reasoning tasks to Nemotron 3 Super.
Deploy and Fine-Tune: Utilize NVIDIA’s open resources and deployment cookbooks (vLLM, SGLang, TensorRT-LLM) to customize and run the model on your own infrastructure.
SPEAKERS Utkarsh Uppal - Solutions Architect, Applied Deep Learning, NVIDIA
Utkarsh Uppal is a senior applied deep learning solutions architect at NVIDIA, where he specializes in building high-performance deep learning pipelines across domains like language and speech. His primary focus is on developing end-to-end conversational AI systems, including training LLMs from scratch, particularly for Indic languages and building domain-specific models with enterprises. He also has deep expertise in designing and optimizing inference architectures for production, with a focus on low-precision formats (FP4, FP8), decoding strategies, and KV-cache optimizations.
LinkedIn: https://www.linkedin.com/in/utkarsh-uppal-b1799a127/
Amol Bhore - MD and CEO of Skymeric Technologies
Amol Bhore is a technology leader with over 20 years of experience specializing in digital transformation across the manufacturing and IT sectors. He currently spearheads a patented, end-to-end Generative AI and RPA platform delivered through a strategic HPE OEM-ISV partnership, focusing on scalable solutions for BFSI, healthcare, and industrial verticals. With a deep background in solution architecture and strategic alliances with HPE and Microsoft, Amol focuses on bridging the gap between complex infrastructure and high-impact enterprise AI applications.
LinkedIn: https://www.linkedin.com/in/amol-bhore
Rohit Anurag - Principal Data Scientist, Partex AI
With over a decade of experience in large-scale AI and search systems, Rohit specializes in foundation models, agentic AI, and high-performance LLM infrastructure. Currently leading the development of a 24B-parameter proprietary healthcare foundation model, he manages large-scale pretraining on clusters of over 300 NVIDIA H100 and B200 GPUs utilizing SLURM. He is also a US patent holder and a published author.
LinkedIn: https://www.linkedin.com/in/rohitanurag
PREREQUISITES
Languages/tools - Python
Sign-up with build.nvidia.com and create your account
Bring your fully-charged laptop as well as the charger to this workshop. Preferably bring your personal laptop as some company laptops may have restrictions on website or AI access.
FEE This meetup is FREE to attend but seats are limited and available on an invite-only basis. Prior registration is required for receiving an invitation, as per the below process.
REGISTRATION To register, please do BOTH of the following:
Fill in your details in this Luma form by clicking "Request To Join"
Download the Deep Tech Stars app here: https://www.deeptechstars.com/about-us/app (optional referral code for signing up: DTSNVID10)
You must follow the above procedure and receive an official invite. Please note that we will not be able to accommodate walk-ins at the event.
CONTEST We have a contest at this event! The top 5 projects, the top 5 blogs, and top 5 papers about Nemotron 3 will each receive some cool NVIDIA swag! So make sure you participate and share your learning from the event in the form of a project, blog or paper. You can make the submission by sending the link to us at info@deeptechstars.com.
Early bird prizes: We have some early bird prizes, available for the first 5 submissions! If you have already done some work on Nemotron 3, you can submit your project, blog or paper in the application form directly or by emailing it to us at info@deeptechstars.com.
USEFUL LINKS
Introducing Nemotron 3 Super: An Open Hybrid Mamba-Transformer MoE for Agentic Reasoning – Blog
NVIDIA-Nemotron-3-Super-120B-A12B-FP8 – Model Repository on HF
Tutorial on Nemotron 3 Super: Multi-Token Prediction, Latent MoE, Perplexity and OpenCode Integration – Video
New NVIDIA Nemotron 3 Super Delivers 5x Higher Throughput for Agentic AI – Blog
Creating your own computer use agent - Blog
Please reach Nihal at 9663374431 and Talib at 7977757472 if you need any clarifications or have any challenges in registration. We look forward to seeing many of you there!
Our thanks to NVIDIA and FAIR (Folks in AI Research) for collaborating with us for this session, and special thanks to our Venue Partners Coditas for hosting us. Blasts Nihal Kashinath 7 May, 2:05 pm Logistics details for attending NVIDIA Nemotron 3 Super – Workshop in Pune
Hello,
Congratulations again on receiving the official invitation to the workshop "NVIDIA Nemotron 3 Super – Workshop" in Pune. Please find below the logistics details to attend the session on Saturday, May 9, 10:00 AM at the Coditas office. Please plan to arrive by 9:15 AM at the venue to allow time for security check.
Things to bring:
A valid Government-issued ID card - Without this you will not be allowed past front gate security. Very important.
Laptop - Please bring your fully charged laptop along with charger. Best to bring your personal laptop rather than a company laptop, as they may have some restrictions on which websites/tools/software can be accessed.
Sign-up with build.nvidia.com and create your account
App - Please have the Deep Tech Stars app installed for quick check at the venue entrance. You can download it here if you haven't done so already: https://www.deeptechstars.com/aboutUs/app (optional referral code: DTSNVID10 - case sensitive).
QR Code - Keep the QR Code from Luma ready for scanning and marking attendance at the entry. You will have received a confirmation email with a button saying "My Ticket", you can get the QR code there. Check your spam folder once if you are unable to find it. The fact that you are receiving this email means you have already been issued a ticket.
Venue details:
Address: No. 33, 3rd Floor, Gaia Apex, S, 2D, Viman Nagar, Pune, Maharashtra 411014 Map: https://maps.app.goo.gl/8ntzu6wP7azLbSVZ6
While we have made provisions for a large audience this time, if the turnout is larger than expected, entry to attendees will be on a first come first served basis after scanning the QR code in the ticket sent by Luma.
Please arrive early, by 9:15 AM, as the security check process takes time and we will not be able to wait beyond the scheduled start time of the event. Event will start by 10:00 AM sharp.
If you need any assistance at the venue, please reach out to Nihal at 9663374431. If you can't attend for any reason, please cancel your registration on Luma so that we can plan logistics accordingly.
Looking forward to seeing you there!