Hardware Engineer
Job Title: Hardware Engineer – AI Super Computer
Location: Malaysia
Job Type: Full-Time
Company Description:
Asrix Prime is located at Empire Subang SS16 and is led by experienced and leading AI scientists. Asrix is undertaking research & development (R&D) of artificial intelligence (AI) applications and infrastructure for some internationally listed companies (Nasdaq & LSE London).
Asrix stands for A*pplied Scientific Research Information eX*change. Asrix is also a research partner with UPM Business School and UM Computer Science Faculty.
Our vision is to Preserve Human Knowledge and Experience
We already have and are further developing our in-house expertise and resources in the AI area while working on several on-going projects. Among others, we are working on the following areas:
1. Digital Human Twin.
2. Machine learning.
3. Speech recognition.
4. Natural Language Processing.
5. Computer Vision.
6. Artificial General Intelligence
We are seeking a highly skilled and motivated Hardware Engineer to join our team and work on improving the efficiency of GPU supercomputers.
Job Description:
As a Hardware Engineer specializing in GPU supercomputer efficiency improvement, you will be responsible for optimizing the performance and reliability of our GPU-based computing systems. You will work closely with our research and development team to design, assemble, and code solutions that maximize the capabilities of our supercomputing hardware.
Key Responsibilities:
- Supercomputer Configuration and Assembly:
- Design and build custom computer systems for machine learning workloads using consumer-grade components, ensuring compatibility of motherboard and GPU selection.
- Troubleshoot hardware issues and implement solutions for enhanced reliability.
- GPU Optimization:
- Optimize GPU settings for maximum performance while minimizing power consumption.
- Overclock GPUs and fine-tune settings to achieve optimal results.
- Parallel Computing and Cluster Management:
- Develop and maintain GPU clusters for parallel computing tasks.
- Implement cluster management and job scheduling for efficient resource utilization.
- Performance Testing:
- Conduct benchmarking and performance testing on supercomputers to identify bottlenecks and areas for improvement.
- Utilize benchmarking tools and software to assess system performance.
- Code Optimization:
- Work with software developers to optimize GPU-accelerated applications and algorithms.
- Implement code improvements to enhance computational efficiency.
- Power Efficiency Enhancement:
- Investigate and implement power-saving techniques to reduce energy consumption.
- Ensure that supercomputers meet energy efficiency standards.
- System Monitoring and Maintenance:
- Implement monitoring systems to track hardware performance and identify issues proactively.
- Perform routine maintenance and hardware upgrades as needed.
- Documentation:
- Maintain detailed documentation of configurations, optimizations, and improvements.
- Create user guides and manuals for the efficient use of supercomputing resources.
Other requirements
· Familiarity with Linux operating system and shell scripting.
· Experience in programming with Python or C++.
· Knowledge of network architecture and security.
· Familiarity with cloud computing services such as AWS or Azure.
Qualifications:
· Bachelor's or Master's degree in Electrical Engineering, Computer Engineering, or a related field.
· Proven experience in configuring and optimizing GPU supercomputers.
· Proficiency in GPU cluster management and parallel computing.
· Strong coding skills in languages like CUDA, OpenCL, and Python.
· Knowledge of hardware monitoring tools and performance testing.
· Experience with power efficiency enhancements in HPC environments.
· Strong problem-solving and troubleshooting abilities.
· Excellent communication and teamwork skills.
If you are passionate about building high-performance hardware systems for machine learning, with expertise in motherboard compatibility, GPU selection, CPU and memory manipulation, and have a strong desire to work in a dynamic and collaborative environment, we encourage you to apply for this exciting opportunity
If you are a highly motivated hardware engineer with a passion in making significant impact in the field of high-performance computing, we encourage you to apply. Join our team and be at the forefront of innovation in the world of supercomputing.
Job Type: Full-time
Pay: RM4,500.00 - RM6,500.00 per month
Benefits:
- Additional leave
- Cell phone reimbursement
- Health insurance
- Maternity leave
- Opportunities for promotion
- Parental leave
- Professional development
Schedule:
- Monday to Friday
Work Location: In person
Application Deadline: 03/31/2025
Expected Start Date: 04/02/2025