Cenny Wenner
Staff LLM Engineer at Tandem Health
Stockholm, Sweden
Summary
👤
Senior🎓
Top SchoolCenny Wenner is a Staff LLM Engineer based in Stockholm with a decade of experience turning theoretical insights into production-grade AI, ML, and optimization systems. With a PhD background in theoretical computer science and a track record from infectious-disease modeling to customer-facing ML at Mavenoid, Cenny blends rigorous algorithmic thinking with pragmatic engineering to boost performance and reliability. He has led ML teams, co-founded a machine-learning SaaS, and produced tangible wins such as a 97% accuracy result on a real customer-query dataset and large performance speedups in simulation code. An active algorithm developer and contributor to projects like hugapi/hug, he pays careful attention to data serialization, type correctness, and test coverage. Curious about heuristics, mathematical modelling, and alignment, he favors solutions that are controllable, optimizable, and suited for real-world integration.
10 years of coding experience
5 years of employment as a software developer
Doctor of Philosophy (Ph.D.) Computer Science, Doctor of Philosophy (Ph.D.) Computer Science at KTH Royal Institute of TechnologyBachelor’s Degree Mathematics and Computer Science, Bachelor’s Degree Mathematics and Computer Science at Lund University
English, Swedish
Stackoverflow
1reputation
0reached
0answers
0questions
Github Skills (7)
json10
api10
python10
apidoc10
numpy10
testing10
pytest9
Programming languages (6)
Github contributions (5)
hugapi/hug
Jun 2018 - Dec 2018
Embrace the APIs of the future. Hug aims to make developing APIs as simple as possible, but no simpler.
Role in this project:
Back-end Developer & QA Engineer
Back-end Developer & QA EngineerContributions:13 commits, 1 PR in 6 months
Contributions summary:Cenny primarily contributed to improving the output format functionality of the API. They added support for various NumPy data types within the JSON output format, including integers, floats, strings, and booleans. Additionally, they added extensive tests to validate the correct conversion of these NumPy types. Their commits demonstrate a focus on API correctness and data serialization.
api-clientapipythondevelopinghug
Mavenoid/prompt-hyperopt
Jul 2021 - Nov 2022
Improve prompts for e.g. GPT3 and GPT-J using templates and hyperparameter optimization.
Contributions:165 commits, 7 PRs, 5 pushes in 1 year 3 months
template-enginepytorchpromptshyperparameteroptimization
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.