Finde einen Job 
Finde eine Ausbildung 
Top Arbeitgeber 
Top Universitäten 
Für Unternehmen Auf einen Blick
- Aufgaben: Build a scalable inference framework for cutting-edge AI hardware.
- Arbeitgeber: Join SEMRON, a startup revolutionizing AI hardware for Edge devices.
- Mitarbeitervorteile: Collaborate with top talent and contribute to open-source projects.
- Warum dieser Job: Work at the forefront of AI and hardware innovation with a dynamic team.
- Gewünschte Qualifikationen: Strong skills in PyTorch and CUDA; knowledge of quantization methods required.
- Andere Informationen: Opportunity to influence architectural decisions and push performance boundaries.
Das voraussichtliche Gehalt liegt zwischen 48000 - 84000 € pro Jahr.
About the Role
We’re SEMRON, a venture-backed startup focused on redefining AI hardware for Edge devices. If you’re deep into quantization and enjoy working at the intersection of machine learning and hardware, we’d like to hear from you. In this role, you will be responsible for building a highly scalable inference framework for our future chip generations. You will participate in fundamental architectural decisions and have the opportunity to contribute to upstream open-source projects.
What you will do:
- Develop and maintain an inference framework that’s tightly tuned for SEMRON hardware.
- Collaborate directly with ML, compiler, and hardware teams to refine and adapt quantization algorithms for our specific needs.
- Apply and innovate on the latest quantization methods like AdaRound, BRECQ, GPTQ, and QuaRot, bringing fresh ideas to SEMRON’s approach.
What you should bring in:
- Solid skills in PyTorch and experience with torch.FX, plus the know-how to write efficient, custom CUDA kernels.
- A solid understanding of current quantization research and hands-on experience with techniques that push performance.
Helpful but not required:
- Experience with State-of-the-art NN compression methods like Adaround, QDrop, QUIP, or GPTQ.
- Experience with typical tools used in ML environments like HuggingFace’s transformers or DeepSpeed.
Why us?
#J-18808-Ljbffr
ML Quantization Engineer Arbeitgeber: SEMRON GmbH
Kontaktperson:
SEMRON GmbH HR Team
StudySmarter Bewerbungstipps 🤫
So bekommst du den Job: ML Quantization Engineer
✨Tip Number 1
Familiarize yourself with the latest quantization methods like AdaRound, BRECQ, and GPTQ. Being able to discuss these techniques in detail during your interview will show your deep understanding of the field and your readiness to contribute to SEMRON's innovative approach.
✨Tip Number 2
Highlight any experience you have with PyTorch and torch.FX, especially if you've written custom CUDA kernels. This technical expertise is crucial for the role, and demonstrating your hands-on skills can set you apart from other candidates.
✨Tip Number 3
Engage with open-source projects related to ML and quantization. Contributing to these projects not only enhances your skills but also shows your commitment to the community and your ability to collaborate effectively, which is essential for this role.
✨Tip Number 4
Network with professionals in the AI hardware space. Attend relevant conferences or meetups where you can connect with others who share your interests. This can lead to valuable insights and potentially even referrals for the position at SEMRON.
Diese Fähigkeiten machen dich zur top Bewerber*in für die Stelle: ML Quantization Engineer
Tipps für deine Bewerbung 🫡
Understand the Role: Make sure to thoroughly read the job description for the ML Quantization Engineer position at SEMRON. Understand the key responsibilities and required skills, especially focusing on quantization methods and experience with PyTorch.
Highlight Relevant Experience: In your application, emphasize your experience with quantization algorithms and any projects where you've developed or maintained inference frameworks. Mention specific techniques like AdaRound, BRECQ, or GPTQ that you have worked with.
Showcase Technical Skills: Clearly outline your technical skills in your CV, particularly your proficiency in PyTorch, torch.FX, and CUDA. Provide examples of how you've applied these skills in past projects or roles.
Tailor Your Cover Letter: Write a personalized cover letter that connects your background to SEMRON's mission. Discuss your passion for AI hardware and how your innovative ideas can contribute to their future chip generations.
Wie du dich auf ein Vorstellungsgespräch bei SEMRON GmbH vorbereitest
✨Showcase Your Quantization Knowledge
Be prepared to discuss your understanding of quantization methods like AdaRound, BRECQ, GPTQ, and QuaRot. Highlight any projects or experiences where you've applied these techniques, as this will demonstrate your expertise and fit for the role.
✨Demonstrate Your PyTorch Skills
Since solid skills in PyTorch are essential, be ready to talk about your experience with torch.FX and how you've used it in past projects. If possible, bring examples of custom CUDA kernels you've written to showcase your technical abilities.
✨Collaborative Mindset
This role involves collaboration with ML, compiler, and hardware teams. Prepare to discuss how you've successfully worked in cross-functional teams in the past, emphasizing your communication skills and ability to adapt to different perspectives.
✨Stay Updated on Current Research
Familiarize yourself with the latest research in quantization and neural network compression methods. Being able to discuss recent advancements or trends will show your passion for the field and your commitment to continuous learning.