Job Description

Embedded LLM is a pioneering force in the AI industry, focusing on Large Language Models (LLMs) to transform enterprise operations. Our mission is to democratize AI technology, making the power of LLMs accessible to businesses of all sizes. We specialize in integrating open-source LLMs into business environments, offering professional quality assurance, and robust customer support. We are committed to innovation, collaboration, and growth, and we are looking for like-minded individuals to join our team.
We are looking for a dedicated GPU Software Engineer with a specialization in AI/LLM Inference to enhance our team. The successful candidate will be instrumental in developing and optimizing LLM inference algorithms specifically for GPU platforms, contributing to our No-Code Platform\'s capabilities, and ensuring that our clients can leverage the full potential of their data with unparalleled performance.

Responsibilities:

• Design and implement high-performance LLM training and inference infrastructure on GPU clusters.
• Perform in-depth performance analysis, benchmarking, and tuning of LLMs on various GPU architectures.
• Keep up-to-date with the latest advancements in AI, machine learning, GPU computing, and LLMs to continuously improve our offerings.
• Provide technical expertise to our consultancy services, assisting clients in adopting LLM technologies effectively.
• Maintain and document software functionality, adhering to coding standards and best practices.
• Contribute to the development and maintenance of our open-source projects, ensuring quality and community engagement.
• Engage with the open-source community, review code contributions, and collaborate with external developers to enhance our projects.

What We Offer:

• Competitive salary and benefits package.
• A collaborative, inclusive, and dynamic work environment.
• Professional development opportunities in a cutting-edge technological field.
• The opportunity to make a substantial impact in the AI industry.

Our Values: Embedded LLM is built on a foundation of innovation, democratization of AI, and collaborative development. We value creative thinking, diverse perspectives, and a culture where taking risks is encouraged. Professional growth, meritocracy, and a casual yet productive work environment are the pillars of our company culture.

Join Us: If you are passionate about AI and GPU technology and are ready to contribute to a team that is shaping the future of enterprise data transformation, we would love to hear from you. Apply now to become a part of Embedded LLM, where your work will not just be a job, but a journey of innovation and growth.

How to Apply: Please send your resume, cover letter, and any relevant work samples or GitHub profile link to info@embeddedllm.com. We are looking forward to your application!

Embedded LLM is an equal opportunity employer. We celebrate diversity and are committed to creating an inclusive environment for all employees.

[Apply now at https://my.hiredly.com/jobs/jobs-malaysia-embedded-llm-job-gpu-software-engineer-ai-llm-infrastructure]

; Requirements: - Job Requirements:

• Bachelor\'s degree in Computer Science, Computer Engineering, or related field.
• Demonstrated experience in AI and machine learning, with a focus on GPU performance optimization.
• Proficiency in programming with C/C++ and Python in a Linux environment.
• Experience with deep learning frameworks such as PyTorch, DeepSpeed, vLLM or similar.
• Strong understanding of GPU computing, CUDA, and optimization techniques.
• Exceptional problem-solving skills and a passion for AI innovation.
• Excellent communication skills and the ability to work effectively in a team setting.

Nice to Have:

• Experience with AMD ROCm platform or other GPU computing platforms.
• Contributions to open-source projects and active engagement with open-source communities.