Working Student - AI Engineer LLM Quantization

On-site | Part-time (20 hours per week)

About Recogni

Artificial intelligence (AI) is transforming our world. It can perform cognitive functions that previously only humans could do, such as perceiving interactions across different environments with the ability to quickly learn and then solve complex problems. Recogni is a system solution company that specializes in the design of industry-leading high-performance, low-power AI inferencing. Our mission is to enable multimodal Generative AI inference acceleration at scale by providing safe, sustainable, high-performance AI-driven solutions for many markets. We are at the leading edge of advancing the latest research and product improvements for Al inference solutions that will make Al even more advantageous for compelling new applications. Recogni is a well funded, fast-paced startup company with headquarters in both San Jose, CA, and Munich, Germany. We also have many talented team members working remotely. We prioritize our employees' well-being and their families, aiming for a healthier, happier life inside and outside work. We value their contributions and offer tailored benefits for health and financial security, catering to different life stages. Our comprehensive benefits and competitive compensation, including flexible spending and Bonusly awards, reflect our commitment to a supportive and inspiring work environment.

About the Role

To keep pace in this dynamic, interdisciplinary field of large language model (LLM) acceleration, we are looking for a working student to join our quantization and compression team. You will play a pivotal role in advancing our post-training quantization (PTQ) methods for LLMs, in particular mixed-precision algorithms. If you are passionate about compressing neural networks and running them efficiently, then we’d love to talk!

Your Responsibilities

• Develop and improve quantization techniques: Experiment with state-of-the-art post-training quantization (PTQ) methods to improve model efficiency for deployment on our ASIC hardware.
• Benchmark and evaluate quantization strategies: Conduct rigorous testing and analysis of different quantization approaches, understanding what methods work best in combination with our hardware.
• Enhance our quantization software stack: Improve our PTQ workflow by developing robust, efficient, and scalable code.
• Collaborate with hardware and ML teams: Work closely with ASIC designers and ML researchers to co-optimize software and hardware for efficient execution of quantized models.

Your Qualifications

• Educational Background: You are currently pursuing a Master’s program in Computer Science, Electrical Engineering, Machine Learning, or a related field, with coursework in the field of deep learning. Experience with LLMs is a plus.
• Experience with Quantization: Familiarity with PTQ for LLMs. Hands-on experience is a plus.
• Proficiency in Python and ML Frameworks: Strong programming skills in Python and experience with ML frameworks such as PyTorch.
• Strong Analytical and Problem-Solving Skills: Ability to understand research papers, conduct experiments, and analyze results.

Reasons to consider joining Recogni

• Pioneer Status: Join us at the ground floor and contribute to shaping one of the most thrilling and innovative companies in its early stages.
• Continuous Learning: Engage in valuable learning and development experiences within a dynamic and diverse peer group. Benefit from the expertise of individuals spanning various fields, including Artificial Intelligence & Computer Vision, as well as Systems & Device Engineering.
• Competitive Compensation: Enjoy a competitive compensation package that reflects your skills and contributions.
• Perks Galore: Take advantage of enticing perks such as corporate discounts, snacks and drinks, and company events.
• Dynamic Work Environment: Collaborate with sharp and motivated colleagues in a stimulating office setting designed for both productivity and enjoyment.
• Invest in Your Future: If transitioned to a Permanent employee status - Participate in our Employee Stock Purchase Plan to align your success with the company's growth.
• Work-Life Balance: Embrace flexibility with options like flexible work hours with a generous allocation of 27 vacation days(apportioned). Achieve the balance that suits your lifestyle.

Recogni's culture was built on the following values that are equally important to us as business:

• Put people first. We only succeed when our people succeed.
• Ethics and integrity always; Being open, honest, and respectful of everyone.
• Think Big. Be ambitious and have audacious goals.
• Aim for excellence. Quality and excellence count in everything we do.
• Own it and get it done. Results matter!
• Make each person better together than they would be as an individual.
• Embrace each others’ differences.

   

Recogni is an equal opportunity employer. We believe that a diverse team is better at tackling complex problems and coming up with innovative solutions. All qualified applicants will receive consideration for employment without regard to age, color, gender identity or expression, marital status, national origin, disability, protected veteran status, race, religion, pregnancy, sexual orientation, or any other characteristic protected by applicable laws, regulations and ordinances.

A note to Recruitment Agencies: Please don’t reach out to Recogni employees or leaders about our roles -- we’ve got it covered. We don’t accept unsolicited agency resumes and we are not responsible for any fees related to unsolicited resumes. Thank you for your understanding.