Machine Learning Engineer

You'll develop and deploy ML models from predicting circuit performance to optimizing features, such as power efficiency. This is a high-impact role where your models will directly influence how engineers design next-generation semiconductors.

This role requires in-person work at our San Francisco or Taipei office.

Leafy Lab

Leafy Lab is redefining semiconductor design with explainable AI. Our technology aims to deliver 95%+ prediction accuracy and reduce chip development time by up to 50%. By combining AI, device physics, and semiconductor engineering, we build next-generation modeling and circuit design tools that address the industry’s hardest technical challenges. Our platform is trusted by the world’s top 10 chip design companies and backed by leading Silicon Valley investors. Every engineer directly shapes our product and the future of AI-driven chip design.

Key Responsibilities

Design, train, and optimize machine learning models for semiconductor chip performance prediction and layout optimization
Build explainable AI systems that chip designers can trust and understand, making model predictions actionable
Work with limited datasets to develop robust models that generalize well across different design conditions
Collaborate with domain experts (semiconductor engineers) to incorporate physics-based insights into ML architectures
Deploy and maintain models in production environments, including containerized on-premises customer deployments
Iterate on model performance based on real-world feedback from customers of top global chip design companies
Contribute to research and potentially publishable work in AI for semiconductor design

Qualifications

Bachelor's degree in Computer Science, Electrical Engineering, Physics, or equivalent practical experience
5+ years of experience in machine learning engineering or applied ML research
Strong foundation in machine learning fundamentals: supervised learning, model evaluation, feature engineering, and hyperparameter optimization
Proficiency in Python and ML frameworks (TensorFlow, PyTorch, scikit-learn)
Experience working with small to medium-sized datasets and techniques for handling data limitations
Understanding of model interpretability and explainable AI techniques
Ability to translate business requirements into technical ML solutions
Strong software engineering practices: version control, testing, documentation

Nice to Have

Experience with decision trees, random forests, support vector machines, or other interpretable ML methods
Background in physics, materials science, or electrical engineering
Knowledge of semiconductor devices, transistor physics, or EDA tools
Experience deploying ML models in production or customer environments
Familiarity with containerization (Singularity, Docker, Kubernetes) and MLOps practices
Publications in ML conferences or journals
Experience with neural networks and deep learning architectures

Why Join Leafy Lab

Real Industry Impact: Build tools used by global engineering teams to accelerate next-generation AI and chip development
Deep Technical Challenges: Tackle complex ML × device physics × EDA problems, including high-precision modeling and explainable AI
Full-Stack Technical Growth: Develop across chip design, device modeling, AI algorithms, and system-level tooling
High Ownership and Influence: Early engineers shape our architecture, product direction, and long-term technical vision

How to Apply

Send your resume, GitHub/portfolio (if available), and a brief note about an ML problem you've solved with limited data or that required model interpretability to business@leafylab.io with the subject line “Machine Learning Engineer – [NAME]”