sujee.dev

Fine-Tuning vs. Distillation vs. Quantization, Explained with LEGO

Fri, 04 Sep 2026 00:00:00 +0000

Fine-tuning, distillation, and quantization sound similar but solve different problems. This LEGO explainer shows how.

{AI} in Production with Inngest, Nebius Token Factory, Flox, & MiniMax

Tue, 25 Aug 2026 00:00:00 +0000

Presented ‘coding with open models’

Physical AI Sprint Hackathon

Mon, 17 Aug 2026 00:00:00 +0000

Hackathon support.

Clawcamp SF Summer 2026

Sat, 15 Aug 2026 00:00:00 +0000

Gave a talk on Coding with Open Models.

Kimi K3 Webinar

Wed, 12 Aug 2026 00:00:00 +0000

Organized and hosted a joint Webinar with Kimi team on the release of Kimi K3 model on Nebius Token Factory.

AI4 Conference Las Vegas - 2026

Tue, 04 Aug 2026 00:00:00 +0000

Demoed Token Factory and engaged with developers and attendees at the Nebius booth.

AI Engineer World's Fair - 2026

Mon, 29 Jun 2026 00:00:00 +0000

Gave a talk on Optimizing Open Models for Production alongside Dylan Bristot.

Clawcamp SF

Wed, 24 Jun 2026 00:00:00 +0000

Delivered the talk: Adding real time intelligence to OpenClaw using Tavily and Token Factory.

Berkeley Skydeck Workshop

Wed, 17 Jun 2026 00:00:00 +0000

Ran a Token Factory workshop at Berkeley SkyDeck (Batch 22)

Butter Base Hackathon

Sat, 13 Jun 2026 00:00:00 +0000

Supported Butter Base Hackathon in Sunnyvale, CA.

PyData London - 2026

Sat, 06 Jun 2026 00:00:00 +0000

Delivered a talk ‘Coding with open models’.

NVIDIA Hack for Impact London

Fri, 05 Jun 2026 00:00:00 +0000

Supported the event through Token Factory, and I gave a kickoff talk on Token Factory and open models.

Builders Brews London

Wed, 27 May 2026 00:00:00 +0000

Co-hosted a Builders & Brews meetup in London with Tavily, supporting developers with Token Factory credits and technical Q&A.

Nebius London Build - 2026

Thu, 21 May 2026 00:00:00 +0000

Co-presented a session on ‘Adding real time intelligence to OpenClaw using Tavily and Token Factory’.

Berkeley Skydeck Office Hour

Thu, 14 May 2026 00:00:00 +0000

Ran an office hour at Berkeley SkyDeck.

Langchain Interrupt SF 2026

Thu, 14 May 2026 00:00:00 +0000

Demo: “Deep agents + Tavily + Nebius Token Factory”

Nebius Build Berlin - 2026

Tue, 28 Apr 2026 00:00:00 +0000

Gave a talk ‘Optimizing Open Models for Production’ alongside Dylan Bristot.

AI Builder Club

Thu, 16 Apr 2026 00:00:00 +0000

Talk: Building with open models.

HumanX Conference - 2026

Wed, 08 Apr 2026 00:00:00 +0000

Talk: Optimizing Open Models for Production.

From Production LLM Logs to Better Models

Thu, 26 Mar 2026 00:00:00 +0000

Hosted a webinar on turning production LLM logs into better models - observability and evaluation techniques for inference workloads.

NVIDIA GTC - 2026

Mon, 16 Mar 2026 00:00:00 +0000

Created and ran demos on Token Factory at the GTC booth.

Nebius Build SF - 2026

Sun, 15 Mar 2026 00:00:00 +0000

Very first event on the ‘Nebius Build’ series - a pre-GTC workshop and hackathon in San Francisco. Organized / presented / supported the event.

Post-Training for Production Webinar

Thu, 26 Feb 2026 00:00:00 +0000

Webinar on post-training techniques for running open-source LLMs in production.

NVIDIA Cosmos Cookoff - 2026

Fri, 30 Jan 2026 00:00:00 +0000

Supported the NVIDIA Cosmos Hackathon - building on NVIDIA Cosmos models, alongside Nebius. Provided platform credits and supported participants.

Another Happy Linux Mint User

Sat, 27 Dec 2025 00:00:00 +0000

Linux Mint 22 installation with best practices for disk partitioning and painless upgrades

The Production Playbook for Open-Source LLMs: Fine-Tuning & Distillation

Thu, 18 Dec 2025 00:00:00 +0000

Webinar on the production playbook for open-source LLMs, covering fine-tuning, distillation, and deployment techniques.

AI Summit NYC - 2025

Wed, 10 Dec 2025 00:00:00 +0000

Talk: Optimizing Open Models for Production.

Nebius Builder Hour - 2025

Tue, 09 Dec 2025 00:00:00 +0000

Hosted the first Nebius Builder Hour, a one-hour online session for developers building with Nebius Token Factory. Covered what’s new in Token Factory, live builder demos, and open discussion.

QCon SF - 2025

Thu, 20 Nov 2025 00:00:00 +0000

Ran two workshops at QCon SF 2025 in San Francisco - one on chatting with your website using an LLM and an open stack (Allycat), and another on an open-source RAG pipeline with Docling, Data Prep Kit, and Milvus.

Tech Equity AI Summit - Fall 2025

Fri, 07 Nov 2025 00:00:00 +0000

Ran a workshop on Allycat at Tech Equity AI Summit

Meld - a diff tool for MacOS

Wed, 05 Nov 2025 00:00:00 +0000

Meld is a great open source diff tool for MacOS

Berkeley AgentBeats Hackathon - 2025

Thu, 16 Oct 2025 00:00:00 +0000

Gave a talk at the Berkeley AgentX/AgentBeats Competition, walking through Nebius Token Factory, demoing a CrewAI research agent, and comparing models.

NextBio Hackathon at UCSF - 2025

Fri, 10 Oct 2025 00:00:00 +0000

Attended the NextBio Hackathon at UCSF in San Francisco, gave a talk on open-source models, and demoed AI Studio. Onboarded attendees to AI Studio.

Developer Relations and Advocacy

Mon, 04 Aug 2025 00:00:00 +0000

I love enabling developers to build amazing stuff! I draw from my experience as software dev and technical trainer.

Portfolio • About • See testimonials of my work

Here are some of my recent DevRel work.

Nebius IBM / AI Alliance MongoDB Intel

Nebius (2025 - Present) 🔗

I am a Developer Relations Engineer for Nebius AI focusing on Nebius AI Studio.

Put together ai studio cookbook with examples and use cases
Building a partner network for collaboration and joint promotions
Reaching into my network to promote programs like Nebius startup program and Nebius partner program.
Presenting at conferences / meetups and building brand awareness.
Kicking off webinar series. And starting an ‘office hour’ series to engage with developers and users
Organizing devrel tasks and priorities internally for better visibility and collaboration from key stakeholders.
Working with development / product teams, on shaping product roadmap and new feature prioritization
Working with events / marketing teams to identify important events to participate.

Portfolio: Sujee Maniyam

Mon, 04 Aug 2025 00:00:00 +0000

AI DevRel Engineer / Developer Advocate • AI/ML Engineer • Software/distributed systems architect • Technical Instructor • Author • Speaker

Skills: Developer Advocacy / Relations • Generative AI • machine learning / deep learning • Data Engineering (Spark, Cassandra, Kafka) • Big Data (Hadoop, Hbase) • Cloud • Open source

📧 Contact: sujee@sujee.dev
💻 Code: github • dev blog • dockerhub
Socials: 🤝 linkedin • 🐦 X: @sujee_dev • 🦋 bluesky: @sujee-dev

Videos

Mon, 04 Aug 2025 00:00:00 +0000

My Youtube channel.

Highlights Recent Explainer Videos

Highlights

Intro Videos: About me • Sample course intro • course wrap up
Nebius AI playlist
Data prep kit series - explaining data prep kit features.

Recent

Explainer Videos

Short (animated) videos explaining concepts.

How neural networks are trained using back propagation
How to train an AI - fun kids version • AI for kids
HDFS operations
YARN workflow

Migrating from Pelican to Hugo using Claude Code

Wed, 30 Jul 2025 00:00:00 +0000

How I migrated my site from Pelican to Hugo using Claude Code

Moving the site to Hugo

Sun, 27 Jul 2025 00:00:00 +0000

Moving the site to hugo

Practical Tips for Running an Effective Unconference

Sun, 09 Mar 2025 00:00:00 +0000

Actionable strategies for running a smooth and successful unconference

Pelican theme reviews

Sun, 23 Feb 2025 00:00:00 +0000

My personal review of some pelican themes

Reviving the dev blog with Pelican

Thu, 20 Feb 2025 00:00:00 +0000

moving the site to pelican

AI for Connectivity Hackathon - 2025

Sat, 25 Jan 2025 00:00:00 +0000

This hackathon focused on open source AI tools. Organized by lablab.ai.

IBM TechXchange Dev Day - 2025

Thu, 23 Jan 2025 00:00:00 +0000

My talk: Preparing data for LLM applications using Data Prep Kit.

Test post

Wed, 01 Jan 2025 00:00:00 +0000

PyData Global 2024

Wed, 04 Dec 2024 00:00:00 +0000

Talk: Preparing Data for LLM Applications Using Data Prep Kit.

NumHack Online - 2024

Thu, 14 Nov 2024 00:00:00 +0000

Numhack is focused on positive social impact using AI. Organized by Pydata and Numfocus.org.

Llama Impact Hackathon, San Francisco - 2024

Sat, 09 Nov 2024 00:00:00 +0000

Ran a workshop on preparing data for LLMs using data prep kit.

Tech Equity AI Summit - 2024

Sat, 26 Oct 2024 00:00:00 +0000

Talk: Preparing Data for LLM Applications Using Data Prep Kit.

IBM TechXchange - 2024

Mon, 21 Oct 2024 00:00:00 +0000

Talk: Streamlining Data Prep for LLMs with Data Prep Kit.

Large Language Model Workshop

Wed, 09 Oct 2024 00:00:00 +0000

This workshop focused on developing LLM applications, covering tokenizers, embeddings, vector search, local LLMs, and RAG.

Data Prep Kit Workshop @ Hacker Dojo - 2024

Sat, 21 Sep 2024 00:00:00 +0000

Ran a hands-on workshop introducing Data Prep Kit. This is the first of the Data Prep Kit series.

Mistral Hackathon, San Francisco - 2024

Sat, 23 Mar 2024 00:00:00 +0000

Developing RAG applications using Mistral LLM.

Developer Week, Oakland - 2024

Wed, 21 Feb 2024 00:00:00 +0000

Vector Search + LLMs with Dave Nielsen of MongoDB.

AI User Conference SF - 2024

Wed, 31 Jan 2024 00:00:00 +0000

Talk: Vector Search with MongoDB + LLMs with Dave Nielsen of MongoDB.

MongoDB Hackathon - 2024

Sat, 27 Jan 2024 00:00:00 +0000

Gave a talk about vector search applications and helped hackathon participants.

Data Science Camp, ACM SV - 2018

Mon, 01 Jan 2018 00:00:00 +0000

Ran a workshop for Data Science in Python.

ODSC West Conference - 2017

Sun, 05 Nov 2017 00:00:00 +0000

Talk: Apache Spark - a hands on workshop.

AWS re:Invent 2017

Wed, 01 Nov 2017 00:00:00 +0000

Presented BigDL framework.

Intel AI Dev Conference

Sun, 01 Oct 2017 00:00:00 +0000

Presented my work on Intel’s BigDL framework.

About: Sujee Maniyam

Mon, 01 Jan 0001 00:00:00 +0000

I’m a developer, technical instructor, and entrepreneur, now focusing on Developer Advocacy / Developer Relations for AI

I have worked with AI/ML, Data Engineering, Distributed Systems, Big Data, and Cloud technologies.

As an AI Developer Relations Engineer, I combine hands-on engineering with community building to help developers make the most of AI, especially open source AI. I also influence/shape the product by providing feedback to dev/product teams. See my developer advocacy work

Adding real time intelligence to Openclaw using Tavily and Token Factory

Mon, 01 Jan 0001 00:00:00 +0000

Enable OpenClaw with real time search with Tavily + Token Factory

Allycat

Mon, 01 Jan 0001 00:00:00 +0000

End-to-end open-source RAG pipeline for website content.

Building with Open Models

Mon, 01 Jan 0001 00:00:00 +0000

Build apps with open models

Coding with Open Models

Mon, 01 Jan 0001 00:00:00 +0000

Using open models with modern coding agents for practical software development.

Community Engagements

Mon, 01 Jan 0001 00:00:00 +0000

Portfolio > Community Engagements

I stay active in developer community. Here are some examples:

Meetups
- Silicon Valley Generative AI meetup
- Big Data Gurus meetup
Community Events

Meetups

Silicon Valley Generative AI meetup (2025 - )

Co-founder of SVGenAI Meetup, focused on emerging technologies in the Generative AI space.

Our events are hybrid—offering in-person gatherings to foster networking and community, while also broadcasting online to reach a broader audience.

Silicon Valley Generative AI @ luma

Courses

Mon, 01 Jan 0001 00:00:00 +0000

Portfolio > Courses

Data Analytics with Spark and Hadoop

Online course published by O’Reilly Media

Guided Machine Learning

Curated Guided Learning - Machine Learning. This guide streamlines the learning process for beginners in Machine Learning, utilizing free, open-source resources. To further assist learners, I held weekly sessions, answering questions ..etc

Data Prep Kit

Mon, 01 Jan 0001 00:00:00 +0000

Open-source tools to cleanse, transform and enrich unstructured data at scale for LLM / RAG workloads.

Data Prep Kit Examples

Mon, 01 Jan 0001 00:00:00 +0000

Companion examples repo for Data Prep Kit

Generative AI

Mon, 01 Jan 0001 00:00:00 +0000

Portfolio > Generative AI

Here is some of my work on GenAI

LLM Snake Arena

Mon, 01 Jan 0001 00:00:00 +0000

LLMs compete in the classic Snake game

My Talks

Mon, 01 Jan 0001 00:00:00 +0000

Portfolio > My Talks

Here are some talks I have done at conferences, hackathons, workshops and meetups.

Jump to a section below:

Conferences • Meetups • Hackathons / Workshops

Highlights

Open Source

Mon, 01 Jan 0001 00:00:00 +0000

I have been an avid user and advocate of open source since the early days of Linux (circa 1995). I also make frequent contributions to open source and authored a few of my own.

github.com/sujee • github.com/elephantscale

My Open Source Projects

Allycat

Allycat is an end to end open-source RAG pipeline for website content. It can

scape websites
clean up content
index content, vectorize and store them in a vector database
and a UI for queries.

The entire stack is open source. It supports LLMs running locally or using an inference service.

Optimizing open models for production

Mon, 01 Jan 0001 00:00:00 +0000

Optimizing open models for production

Practical LLM Evals

Mon, 01 Jan 0001 00:00:00 +0000

Measure LLM inference performance

Publications

Mon, 01 Jan 0001 00:00:00 +0000

Portfolio > Publications

Books

HBase Design Patterns

By Packt Publishing

Co-author.

Introduction to HBase and application design patterns.

HBase Design Patterns

Hadoop Illuminated

Co-author of this open source ebook.
This a gentle introduction of Hadoop and Big Data Ecosystem.
Published: 2013

Hadoop Illuminated website

Services

Mon, 01 Jan 0001 00:00:00 +0000

Get in Touch

sujee@sujee.dev | Book an exploratory call

AI DevRel

As a Developer Advocate, I love empowering developers to create innovative and impactful solutions while providing valuable feedback to shape product roadmaps and features.

I can help you with the adoption of your product leveraging my years of experience, industry connections and reputation.

See some of my developer advocacy work

Select clients

AI Consulting

I can help you implement and ship AI / Data Engineering / Big Data systems. I don’t just give advice - I do the work too.

Sujee Maniyam - Speaker & Instructor

Mon, 01 Jan 0001 00:00:00 +0000

Talks, workshops, speaking videos and resources for conference organizers.

Testimonials

Mon, 01 Jan 0001 00:00:00 +0000

Portfolio > Testimonials

Mike Chrabaszcz, Engineering Leader - Teams, Process, Products: AI, Mobile, IoT

“Thank you for providing a well organized, timely, and insightful workshop at the AI Summit. It is so valuable to be able to learn new tools and have the chance to run the notebooks with such a talented instructor.”

link

Peter J. Theobald, Senior Site Reliability Engineer at Akamai

“Sujee’s workshop on RAG AI with Data Prep Kit, Milvus and LLAMA was one of the best I’ve attended. Clear, concise and hands-on, it really helped me understand all the components to building a LLM pipeline. It was exactly what I needed to kick off an LLM project at work.”

Token Factory Cookbook

Mon, 01 Jan 0001 00:00:00 +0000

Examples and tutorials for Nebius Token Factory

Token Factory workshop

Mon, 01 Jan 0001 00:00:00 +0000

Hands-on with Nebius Token Factory

Workshops

Mon, 01 Jan 0001 00:00:00 +0000

Hands-on workshops on LLMs, coding agents, open models and AI.