Quantization C++ Deep Learning Engineer

Role Overview:
The Staff Engineer will be responsible for architecting and implementing advanced quantization algorithms for edge AI applications. You will lead technical initiatives, mentor junior team members, and drive continuous improvement in model compression and optimization techniques for LLMs and other deep learning models.

Key Responsibilities:
Architectural Leadership:o Design and develop robust quantization strategies and algorithms for AI inference on edge devices.o Lead system-level design discussions and collaborate closely with hardware and research teams.Mentorship & Code Review:o Mentor mid-level and junior engineers, providing technical guidance and best practices.o Conduct thorough code reviews and ensure high standards of quality and performance.Innovation & Optimization:o Stay abreast of the latest research in model quantization and compression, and drive the adoption of innovative techniques.o Develop and maintain performance benchmarks, and continuously optimize algorithms for low latency and high energy efficiency.Cross-Functional Collaboration:o Work with the Quantizer Group Manager and Tech Lead to align technical roadmaps with product objectives.o Participate in regular strategy sessions to set technical direction and priorities.

Qualifications:
Bachelors or Masters degree in Computer Science, Electrical Engineering, or a related field (Ph.D. is a plus).5-8+ years of industry experience in deep learning, model optimization, or related areas.Demonstrated experience with quantization techniques, LLM optimization, and software development using Python/C++.Strong problem-solving skills and a passion for innovation in edge AI technologies.What We Offer:An opportunity to work on pioneering edge AI technologies that redefine the future of real-time inference.A collaborative environment where innovation is at the core of our culture.Competitive compensation, comprehensive benefits, and significant opportunities for professional growth.