Vị trí công việc này hiện tại đã hết hạn nộp hồ sơ, bạn có thể tham khảo thêm một số công việc liên quan phía dưới
Mô tả công việc
Navigos Search's client is seeking engineers to join their team in developing AI software stacks for large-scale deep neural networks, cluster systems, and cloud infrastructure. Their framework is highly optimized for both training and inference across a variety of model architectures, such as large language models (e.g., DeepSeek, Llama) and multi-modal models (e.g., Stable Diffusion and Open-sora).
The GPU
Software Engineers are responsible for a number of technical challenges to quickly run AI applications on various accelerator hardware, including GPUs and NPUs.
Key Responsibilities
• Implementation and optimization of various artificial neural network layers and tensor operations with OpenCL, CUDA, etc.
• Development of performance prediction and analysis models for tensor operation and various accelerators
• Development of code generator and auto tuner to generate and select optimal kernel code for various GPU architectures
• Utilize components of GPU specialized for AI applications (matrix multiplication unit, high-speed interconnection between GPUs, etc.)
• Development of an efficient communication library between GPUs, which includes communication between GPUs located on different nodes
Yêu cầu
• Those who have graduated from an undergraduate degree in computer science or a related major, or have equivalent experience with good results
• Those who are capable of C++ or Python development
• In-depth understanding of computer systems
• Good English communication
• Open to Freshers and those who have less than 2 years of full-time experience after graduation
Preferences
• Experience in competing or winning awards in national and international Informatics, Mathematics, Physics, and Chemistry competitions
• OpenCL or CUDA development experience and knowledge of GPU architecture is a plus point, not required
• Preferential support for professional research personnel
• Master's/Doctoral degree in computer systems or related fields
• Experience in parallelizing/optimizing various AI/HPC applications on GPU and related paper publication history
• Experience developing programs that run on GPU clusters using MPI, NCCL, etc.
• Participation in large-scale software development based on C++
• Basic knowledge of deep learning, experience implementing artificial neural network models- History of paper submissions in major academic conferences (e.g. ASPLOS, HPDC, ISCA, Micro, PACT, PLDI, PPoPP, SC) and other research experience.
Quyền lợi
Thưởng
13th monthly salary
Đào tạo
Learn from experts and professors at top South Korean universities, eg Seoul National University
Giải thưởng
Opportunity for permanent employment after training
Xem thêm
Thông tin khác
NGÀY ĐĂNG
31/03/2025
CẤP BẬC
Mới Tốt Nghiệp
NGÀNH NGHỀ
Công Nghệ Thông Tin/Viễn Thông > Phần Mềm Máy Tính
KỸ NĂNG
C++ Development, Python, English
LĨNH VỰC
Phần Mềm CNTT/Dịch vụ Phần mềm
NGÔN NGỮ TRÌNH BÀY HỒ SƠ
Tiếng Anh
SỐ NĂM KINH NGHIỆM TỐI THIỂU
Không yêu cầu
QUỐC TỊCH
Không hiển thị
Xem thêm
Thông tin chung
- Ngày hết hạn: 30/04/2025
- Thu nhập: $ 1,200-2,000 /tháng
Nơi làm việc
