Senior Software Engineer

We are seeking a highly skilled and hands-on Senior Software Developer with expertise in C++, AI and ML.

It is a fully remote position offering you the flexibility to work from any location in Poland, whether it's your home or one of our well-equipped offices in Gdansk, Katowice, Krakow, Lodz, Warsaw, or Wroclaw.

Responsibilities

• Develop and optimize low-level workloads and kernels to enhance the performance of software for machine learning applications
• Implement tensor compute and tensor data movement optimization kernels
• Design, develop, and maintain kernel-level software components for the client’s machine learning and HPC applications
• Perform in-depth analysis and optimization of low-level code, focusing on improving tensor optimization and efficiency
• Collaborate with machine learning engineers to integrate optimized kernels and routines into frameworks and pipelines
• Identify performance bottlenecks through profiling and apply strategies to resolve inefficiencies
• Conduct comprehensive testing, unit test development, and debugging to ensure the stability and reliability of kernel-level code
• Communicate and problem-solve effectively to analyze and debug complex software issues
• Leverage industry tools for performance profiling and optimization

Requirements

• 3+ years of experience in relevant roles involving low-level programming and optimization
• Proficiency in C/C++ and low-level programming with a focus on kernel optimization
• Background in kernel development, including the implementation of efficient kernels and libraries for machine learning and HPC
• Expertise in low-level optimization techniques, specifically in tensor compute and data movement
• Experience with performance profiling, debugging tools, and strategies for software optimization
• Proven skills in kernel-level software testing, debugging, and development, ensuring efficiency and stability
• Understanding of machine learning pipelines and collaboration between software engineers and data scientists
• Strong problem-solving skills and the ability to resolve bottlenecks in performance-critical environments
• B2 level of English or higher, with an emphasis on technical communication skills

Nice to have

• Familiarity with machine learning frameworks and an understanding of related concepts
• Knowledge of operating system internals
• Understanding and experience with GPU programming such as CUDA or OpenCL