Location
Astana, Kazakhstan, with remote work available within Kazakhstan
Company
EPAM Kazakhstan delivers international engineering projects involving software development and advanced computing technologies.
What you will do
•Design, develop, and optimize high-performance applications using modern C++.
•Implement and tune GPU-accelerated algorithms and CUDA kernels.
•Analyze CPU/GPU performance, profile applications, and eliminate bottlenecks.
•Develop parallel and multithreaded solutions for large-scale scientific and engineering workloads.
•Contribute to HPC architecture, integrate GPU computing into existing systems, and process large datasets.
•Collaborate with international engineering teams through code reviews, technical discussions, and architectural decisions.
Requirements
•3–6 years of professional experience in software engineering.
•Strong commercial experience with C++11/14/17 or later and hands-on CUDA development.
•Experience building or optimizing HPC applications and understanding GPU architecture and memory hierarchy.
•Experience with parallel programming, multithreading, Linux development, performance optimization, and profiling.
•Strong knowledge of algorithms, data structures, and computational efficiency.
•Upper-intermediate or higher English for communication in a global team.
Nice to have
•Experience with multi-GPU systems, OpenMP, MPI, or distributed computing.
•Knowledge of NVIDIA Nsight, nvprof, or other profiling tools.
•Scientific computing or research-oriented project experience.
•Python scripting, automation, Docker, Kubernetes, or cloud environments.
•Experience accelerating AI/ML workloads on GPUs.
Culture & Benefits
•Official employment with long-term career development opportunities.
•Work on an international HPC project with challenging technical tasks and real-world impact.
•Flexible work environment with onsite work in Astana or remote work within Kazakhstan.
•Collaboration with skilled engineers and architects in a distributed international team.
•Professional growth, continuous learning, and exposure to advanced GPU architectures.
•Opportunity to influence technical and architectural decisions for large-scale computing solutions.
