Kale-ab Tessera
PHD Student at The University of Edinburgh
City of Edinburgh, Scotland, United Kingdom
Summary
🤩
Rockstar🎓
Top SchoolKale-ab Tessera is a PhD student at the University of Edinburgh with 11 years of software and ML engineering experience focused on robust multi-agent coordination in dynamic real-world environments. He brings research-grade rigor from roles at InstaDeep and MultiChoice, where he designed and tuned distributed multi-agent RL systems and contributed backend JAX implementations for projects like Mava. Adept at bridging research and production, he has hands-on experience addressing training stability and communication challenges in MADQN-style algorithms. Kale-ab’s background spans full-stack engineering through to advanced ML research, underpinned by an MSc and honours in computer science. Based in Edinburgh, he combines academic inquiry with practical engineering discipline and a track record of improving distributed system performance.
11 years of coding experience
7 years of employment as a software developer
Doctor of Philosophy - PhD, Doctor of Philosophy - PhD at The University of EdinburghMSc Computer Science, MSc Computer Science at University of the WitwatersrandPepps CollegeUniversity of Pretoria
English
Stackoverflow
3reputation
0reached
1answer
0questions
Github Skills (7)
multi-agent-reinforcement-learning10
ml9
jax9
mle9
reverse7
owin6
asp-net-identity6
Programming languages (11)
Github contributions (5)
instadeepai/Mava
Mar 2021 - Jan 2023
🦁 A research-friendly codebase for fast experimentation of multi-agent reinforcement learning in JAX
Role in this project:
Backend Developer & ML Engineer
Backend Developer & ML EngineerContributions:8 releases, 339 reviews, 1230 commits in 1 year 10 months
Contributions summary:Kale-ab appears to be contributing to the DIAL system, a multi-agent reinforcement learning codebase in JAX. Their commits reveal work on configuring and tuning the MADQN algorithm, which may involve incorporating techniques to address potential issues with gradient norms. The user made adjustments to the training process within the MADQN component, and implemented changes to facilitate communication and performance in the distributed system.
multi-agent-systemsmultiagentagentreinforcement-learningreinforcement-learning-agent
KaleabTessera/ICOOmen_ML_Model
Nov 2018 - Jan 2019
Contributions:29 commits, 23 pushes, 1 branch in 1 month
Find and Hire Top DevelopersWe’ve analyzed the programming source code of over 60 million software developers on GitHub and scored them by 50,000 skills. Sign-up on Prog,AI to search for software developers.