Tadej Ciglarič
Senior Software Engineer at Guardiaris
Slovenia
Summary
🤩
Rockstar🎓
Top SchoolTadej Ciglarič is a Senior Software Engineer with 11 years of experience specializing in high-performance C++, SYCL and OpenCL development for GPUs, parallelization and numerical algorithms. He has delivered production-grade contributions to prominent open-source projects like Stan Math and oneDNN, adding GPU backends and probability functions and extending CUDA/USM support to improve deep learning performance. His work spans FFT and deep-learning kernels, compiler backends (PTX/GCN) and automatic differentiation, consistently squeezing near-peak hardware performance across NVIDIA, AMD and Intel GPUs. Comfortable in Python and ML tooling, he blends applied Bayesian/statistics expertise with low-level optimization—evidenced by GPU speedups of tens to hundreds of times in scientific workloads. A mentor and team builder at Codeplay, he also runs tooling and benchmarking for numerical correctness and performance, preferring to contribute remotely from Slovenia and not relocate.
11 years of coding experience
8 years of employment as a software developer
Master's degree Computer Science, Master's degree Computer Science at University of Ljubljana, Faculty of Computer and Information Science
Github Skills (31)
algorithm10
bayesian-statistics10
opencl10
algorithms10
c-language10
probabilistic-programming10
numerical10
bayesian-data-analysis10
gpu-programming10
stat10
distributions10
statistic10
mathematical-optimization10
sycl10
bayesian10
Programming languages (11)
Github contributions (5)
stan-dev/math
Dec 2018 - Jul 2021
The Stan Math Library is a C++ template library for automatic differentiation of any order using forward, reverse, and mixed modes. It includes a range of built-in functions for probabilistic modeling, linear algebra, and equation solving.
Role in this project:
Backend Developer & Numerical Algorithms Specialist
Backend Developer & Numerical Algorithms SpecialistContributions:630 reviews, 1885 commits, 315 PRs in 2 years 8 months
Contributions summary:Tadej's commits reveal a focus on core backend development within the Stan Math Library, particularly the implementation and improvement of numerical algorithms. This includes contributions to the opencl backend, with the addition of features like Gaussian Process covariances and various probability density functions (lpdf) for statistical distributions. The user's work involved both algorithm implementation and testing to ensure accuracy and performance. This indicates a strong focus on low-level optimization and numerical methods.
automatic-differentiationprobabilistic-modelingsundialsmodestemplate-library
stan-dev/stan
Aug 2020 - Jul 2021
Stan development repository. The master branch contains the current release. The develop branch contains the latest stable development. See the Developer Process Wiki for details.
Role in this project:Back-end Developer
Back-end DeveloperContributions:119 reviews, 51 commits, 19 PRs in 11 months
Contributions summary:Tadej primarily contributed to the `stan-dev/stan` repository by implementing and modifying indexing functionalities within the Stan library. The commits focused on refining the `rvalue` and `lvalue` functions, which are crucial for accessing and assigning values within Stan's probabilistic programming language. Their work involved changes to header files related to indexing, including `rvalue.hpp` and `assign.hpp`, and involved adding support for more advanced indexing functionality.
bayesian-inferencestanmasterbayesian-statisticsdetails
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.