AI Inference Engineer

Nabízím práci
Jméno/Firma
High Tech Engineering Center a.s.
Pracoviště
Evropská 2758/11, Praha
Úvazek
Plný
Požadované vzdělání
Bez maturity
Požadované jazyky
Angličtina
Profese
Informatika a IT služby
Nabízím práci/ Hledám práci
Nabízím práci
Vytvořeno
4. 11. 2025

O pozici

Pracovní nabídka

Join a team building the software foundation for next-generation AI compute platforms.
You’ll work across the full technology stack – from low-level kernels and hardware-optimized operators to large-scale ML deployment frameworks – collaborating closely with compiler engineers, ML researchers, and hardware specialists.

Your role will be to help shape cutting-edge AI infrastructure, fine-tune software for custom hardware, and expand your expertise in system software and machine learning.

What you’ll do

  • Design, develop, and maintain components for AI compute platforms
  • Implement and optimize key ML operators (e.g., GEMMs, convolutions, BLAS routines)
  • Map computational graphs from ML frameworks to target hardware
  • Collaborate with compiler and hardware teams on core infrastructure
  • Debug and analyze performance issues at the system level
  • Build scalable and reliable software solutions, ensuring quality through testing and automation


What we’re looking for

  • Bachelor’s degree in Computer Science, Electrical Engineering, Mathematics, or related field
  • 3+ years of professional software development experience
  • Strong skills in C/C++ or Python within Linux environments
  • Good understanding of computer architecture, system software, and data structures
  • Experience with specialized hardware (GPUs, FPGAs, AI accelerators) – CUDA or OpenCL a plus
  • Solid grasp of ML fundamentals and motivation to learn new technologiesResponsible, proactive team player

Nice to have

  • Experience with inference or training frameworks (Triton, PyTorch, TensorFlow, DeepSpeed, ONNX Runtime, TVM, IREE)
  • Familiarity with distributed systems (MPI, Gloo)
  • Performance optimization and ML operator implementation
  • 2+ years developing software targeting AI hardware
  • Contributions to open-source projects (LLVM, PyTorch, TensorFlow, etc.)

What we offer

  • Flexible working hours and on-site/remote arrangements
  • Private medical, dental, and vision insurance with mental health coverage
  • Training programs and workshops
  • Continuous support for career progression
  • Our benefits: https://htec.com/careers/benefits/#