职位描述
The Role
We are seeking a Senior On-Device AI Development Engineer specializing in Personal AI—an expert who blends deep technical expertise in on-device AI with a product-centric mindset. You will develop reusable and modular components on an unified Lenovo AI stack, ensuring high performance, low latency, and efficient resource utilization, to empower the business units . You won’t just execute tasks; you’ll contribute to the technical direction, and build solutions that align with real user needs and business goals. As a key member of the team, you’ll stay ahead of cutting-edge AI trends and translate them into practical, on-device innovations.
What You’ll Do
· Design and develop end-to-end on-device AI prototypes, leveraging expertise in agent orchestration and development frameworks to deliver functional, user-centric solutions.
· Build reusable technical blocks and frameworks for on-device AI, enabling scalability across Lenovo’s product portfolio.
· Optimize models with knowledge of fine-tuning to ensure optimal performance
· Architect and implement cross-platform on-device AI job scheduling mechanisms, enabling seamless execution across diverse hardware and OS environments.
· Collaborate with cross-functional stakeholders (product managers, hardware teams, software engineers) to translate business and user goals into technical requirements and actionable development plans.
· Define and track key metrics (latency, resource utilization, accuracy, power efficiency) to measure prototype and product performance, iterating to drive continuous improvement.
· Stay at the forefront of on-device AI advancements, evaluating new tools, techniques, and frameworks, and advising the team on adoption to maintain technical leadership.
· Communicate complex technical concepts clearly to both technical and non-technical stakeholders, ensuring alignment throughout the development lifecycle.
Qualifications Required (The Must-Haves)
· At least 3 years + experience in personal AI industry
· Proven expertise in on-device AI agent orchestration and proficiency with relevant development frameworks.
· Deep experience with on-device AI inference platforms, with knowledge of on-device model optimization (quantization, pruning, fine-tuning)
· Proficiency in cross-platform on-device AI job scheduling mechanisms, with a track record of delivering solutions across diverse hardware/OS environments. · A scrappy, solutions-oriented mindset with experience thriving in fast-paced, ambiguous environments.
· Expert-level programming skills in Python, Kotlin and C/C++.
· Be able to prototype quickly based on proficient use of AI tools.
· Strong learning agility to keep pace with the rapid evolution of on-device AI technologies and industry trends.
· Excellent communication and presentation skills, with the ability to collaborate effectively in cross-functional teams and articulate technical ideas clearly.
· Fluent spoken English and proficient written English.
· Master’s degree or higher in Computer Science, Artificial Intelligence, Machine Learning, or a related technical field.
Preferred (The Ideal Hire)
· Knowledge or background in Enterprise AI products
· Experience in AI user scenarios across enterprise and on-device
· Familiarity with modern AI stacks (PyTorch/TensorFlow, Hugging Face, vector databases) and cloud AI/ML services (AWS, GCP, Azure) for hybrid on-device/cloud solutions.