Portfolio

Tanay Mehta
March 2023

Abstract

I am a 24-year-old AI Engineer working at Aleph Alpha, Berlin 🇩🇪. I recently completed my Masters in Data Science with Distinction from the University of Bath 🇬🇧, where I worked on generating scaling laws for small language models as my thesis. I am also a Kaggle Notebooks Grandmaster and an avid contributor to major open source ML projects!
I am also looking for ML Engineering / AI Engineering roles actively and if you are hiring, you can contact me at heyytanay@gmail.com.

1. About Me

Mountain landscape
I may look like that but I can assure you, I don't bite.

I am a self-taught programmer and who taught himself Machine learning from Andrew NG's excellent courses on Coursera. In summer of 2020, amid the COVID lockdown in India, I started using Kaggle to enhance his skills and be more competitive in Data Science and Machine Learning. Currently, I am a Notebooks Grandmaster, Competitions Expert and Datasets Expert and my highest rank was #54 in Notebooks category on Kaggle.

2. Education

I am currently a Masters Student (majoring in Data Science) at University of Bath, Somerset, United Kingdom.

Below is the list of formal degrees I have attended / currently attending / will be attending in the near future.

2.1 MSc in Data Science at University of Bath (UofBath)

University of Bath

Major: Data Science

Status: Completed, 2023-2024

Final Grade: Distinction

Dissertation Focus: For my dissertation (Jun '24 - Sept '24), I am generating scaling laws for Large Language models and also searching for phase transitions in LLMs to look for mathematical reasoning and other emergent abilities. I am supervised by Dr Nello Cristianini and my day-to-day work consists of training LLMs with different model parameters, hyper-parameter settings and token sizes and then documenting my findings from these experiments.

2.2 BTech in Computer Science at JECRC University

JU Logo

Major: Computer Science

Minor: Mathematics & Engineering

Status: Completed, 2018-2022

Final Grade: 8.76 / 10.0 (87.6%), First Division

3. Experience

Below you can see all the places I have worked / interned at.

3.1 AI Engineer - Aleph Alpha

Type: Full-time

Duration: November 2024 - Present

About:

3.2 Graduate Teaching Assistant (NLP) - University of Bath

Type: Part-time

Duration: September 2023 - December 2023 (Winter Semester)

About:

4. Open Source Contributions

Below is a tabulated list of all my Open Source contributions.

Pull Request Organization Status
Add Fill-in-the-middle training objective example - PyTorch #27464 huggingface/transformers 🤗 Merged
Add Number Normalisation for SpeechT5 #25447 huggingface/transformers 🤗 Merged
Add PoolFormer #15531 huggingface/transformers 🤗 Merged
Fix Mega chunking error when using decoder-only model #25765 huggingface/transformers 🤗 Merged
Fix MarianTokenizer to remove metaspace character in decode #26091 huggingface/transformers 🤗 Merged
Added Model specific output classes to PoolFormer docs #15746 huggingface/transformers 🤗 Merged
Add LLM Pre-training example #73 lancedb/vectordb-recipes Merged
Add Hinge Loss #409 deepmind/optax Merged
Use monkeypatch.chdir instead of os.chdir in tests #15579 Lightning-AI/lightning ⚡️ Merged

5. Contact Me

I am always up for research and industry collaborations so If you like my work and think we collaborate on something cool, reach out to me via email or message me on Twitter @serious_mehta.
You can also connect with me on LinkedIn, see my projects on Github, see my work on Kaggle or read my blogs on my blog.