AI Inference Expert

Who We Are?

We are a growing startup company revolutionizing the Storage Processor world, with an ingenious solution. Founded in 2017 by industry leaders. We’re the cream of the crop, with a positive disposition, an optimistic vibe, and a can-do attitude.

We’re stronger together, at home and at work. Our mind is sharp and we’re quick on our toes, we lead by sharing, and empower by advising where to look but not what to see. Honestly, we're quite knowledgeable, however, we know there’s a lot more gray matter to color with learning.

Our Extreme Data Processor (XDP) is a hardware-based storage accelerator that enables cloud and enterprise customers to offload and accelerate data-intensive workloads using just a fraction of the computational load and power. It’s truly groundbreaking, you have to see it to believe it.

Pliops does not discriminate on the basis of race, color, religion, sex, sexual orientation, gender identity or expression, national origin, age, disability, veteran status, marital status, or based on an individual's status in any group or class protected by applicable federal, state or local law. Pliops encourages applications from minorities, women, the disabled, protected veterans and all other qualified applicants.

To find out more about us, click on the link below:

Pliops Extreme Data Processor Explained

About The Position

Join our team of expert engineers, driving innovation at the crossroads of advanced storage accelerators and next-gen AI frameworks. You’ll work on impactful applications across generative AI, using Pliops unique hardware. Together, we will push the boundaries of what’s possible in machine learning and AI.

Job Responsibilities

• Develop and enhance products using XDP storage technology, tailored for core ML/AI use cases
• Integrate the XDP KV product into ML/AI applications and frameworks, identifying and driving optimization opportunities based on in-depth knowledge of system architecture and product features
• Design and implement software components across both kernel and user spaces, with capabilities to run efficiently on GPUs
• Research and support new ML/AI use cases to expand product offerings and application possibilities
  
  

• University degree (Bsc/BA in Computer Sciences or Software/Computer/Electrical Engineering)
• Over 8 years of professional software development experience and over 2 years of proven experience in LLM development
• Proficiency in programming languages such as C++/Cuda/Python/Pytorch
• Profound understanding of LLM (Large Language Model) architecture, including performance optimization and scalability
• Hands on with GPU programming languages and frameworks (CUDA/OpenCL), including optimizing experience performance-critical applications - advantage
• Basic knowledge of storage systems, including SSDs, and storage protocols - advantage