About

Hello there 👋

My name is Jithin James aka jjmachan and I’m an ML Engineer from India who is in love with Software Engineering. I think the key to living a meaningful life is to master your craft and use that to help your fellow beings. What both of them exactly mean is upto you/your interests and skills. For me its crafting software and helping my fellow devs bring their visions into reality and naturally I love working in opensource and devtooling with a focus on ML.

I’m working @explodinggradients building tools to help devs building with LLMs especially who are building Retrieval Augmented Generation(RAG) pipelines. We build ragas which is a tools to help evalute RAG pipelines and working on a few other projects as well. My github is where you can find the latest updates.

Previously I used to work with the awesome team @bentoml to build tool that help Data Scientits/ML Engineers with model packaging, deployment and orchestration. BentoML is an open platform that simplifies ML model deployment and enables you to serve your models at production scale in minutes. My primary focus was helping build bentoml/bentoctl which makes it really fast to deploy ML model to the cloud and bentoml/yatai which helps with model deployment at scale on k8s.

I prefer Neovim, i3, tmux in my software development and I tend to prefer tools like these because of how effective they make my workflow. I’ll be putting up a blog about mouse free productivity soon if you want to know more about that.

When I’m not sitting in front of my computer, I’m probably riding my motorbike and I love it! I love travelling, meeting new people and having new experiences. It broadens your view about the world and makes you more emphatic (you also have a shit load of fun, obviously!). I’m also into photography and love films. (I have some blogs lined up about my travels and photography, so check this space later to read them )

Talks

I’ve been fortunate to have been given the opportunity to share my ideas on ML a few times and these are the recordings that were available.

• Desi Open Source Playbook - our learnings about building successfull opensource projects from working on OpenAssistant and BentoML. This is our playbook for building our company.
• Ragas - evalution for RAG pipelines (demo) - Introduce ragas the opensource tool we created for evaluating Retrieval Augmented Generation (RAG) pipelines.
• Neural Nets in 11 lines of code - I talk about building a Neural Network from scratch with just numpy. @School of AI meetup
• Introduction to GANs - An intro to GANs and how to train DCGANs in PyTorch. @Pie and AI - Kochi