Llm-Inference

Gave a talk on Optimizing Open Models for Production alongside Dylan Bristot. Resources AI Engineer World’s Fair 2026 Images

Supported Butter Base Hackathon in Sunnyvale, CA. Images

Supported the event through Token Factory, and I gave a kickoff talk on Token Factory and open models. Talk : Building with open models Resources NVIDIA Hack for Impact London

Nebius Build Berlin. I gave a talk Optimizing Open Models for Production alongside Dylan Bristot. Resources Images

Talk: Optimizing Open Models for Production Images

Hosted a webinar on turning production LLM logs into better models — observability and evaluation techniques for inference workloads. Resources event page - watch webinar replay

Very first event on the ‘Nebius Build’ series - a pre-GTC workshop and hackathon in San Francisco. Organized / presented / supported the event. Ran a Token Factory workshop and mentored builders. Resources Nebius Build SF (event page) register: Cerebral Valley sign-up

Webinar on post-training techniques for running open-source LLMs in production. Resources Post-Training for Production (event page) - watch webinar replay

Talk: Optimizing Open Models for Production