AI Algorithm Developer

Applied Materials is the leader in materials engineering solutions used to produce virtually every new chip and advanced display in the world. Our expertise in modifying materials at atomic levels and on an industrial scale helps our customers – who make smartphones, supercomputers, virtual reality headsets, autonomous vehicles and more – transform their ideas into reality.

Inside our company, we apply the idea of making it possible as we work together. We value our people and teams who turn possibilities into reality by advancing our strategy, accomplishing great things, and empowering others. We are deeply committed to fostering a Culture of Inclusion where every person knows they belong, feels empowered to bring their whole self to work, and is inspired to grow.

Position Overview

We are seeking an AI Algorithm Developer to design and implement machine learning algorithms for semiconductor manufacturing process optimization. This role requires a strong foundation in computer science fundamentals, software engineering best practices, and deep learning/optimization algorithms. You will work on challenging problems involving sparse, noisy, high-dimensional data from semiconductor equipment, building models that predict on-wafer performance from recipe parameters.

The ideal candidate combines algorithmic depth (can reason through "why", not just implement), clean code practices (design patterns, testing, maintainable systems), and critical thinking (customizes algorithms to problem constraints rather than applying cookbook solutions).

Key Responsibilities

• Design and implement deep learning models for semiconductor process optimization (recipe inputs → metrology outputs)
• Develop Bayesian optimization strategies for sample-efficient experimental design with expensive experiments

• Write clean, maintainable, scalable code following software engineering best practices
• Apply design patterns to algorithm implementations
• Develop comprehensive unit tests and validation frameworks for algorithms
• Refactor prototype algorithms into production-quality code integrated with AppliedPRO architecture
• Conduct and participate in code reviews, fostering team code quality standards
• Document design decisions, trade-offs, and algorithmic approaches clearly
• Build surrogate models and active learning frameworks for sparse, noisy manufacturing data
• Create novel algorithms that combine data-driven approaches with domain constraints
• Implement algorithms with proper data structures, computational complexity awareness, and performance optimization

• Translate semiconductor manufacturing challenges into well-defined ML problems
• Reason through trade-offs between accuracy, speed, and maintainability
• Customize algorithms to handle sparse data, noisy measurements, and expensive experiments
• Debug systematically when algorithms underperform (not trial-and-error)
• Propose and implement innovative solutions to complex optimization problems

• Work with domain experts to understand semiconductor process constraints
• Communicate complex algorithmic concepts to non-technical stakeholders
• Collaborate with team members on algorithm design and code architecture
• Contribute to team knowledge sharing on ML techniques and software best practices

Key Requirements

• Computer Science Foundation: Strong understanding of algorithms, data structures, computational complexity
• Software Engineering: Clean code practices, design patterns, unit testing, modular architecture
• Programming: Expert-level Python
• Deep Learning: Neural network architectures, training dynamics, optimization techniques (can explain "why", not just use libraries)
• Optimization Algorithms: Experience with gradient-based methods, Bayesian optimization, or evolutionary strategies
• Critical Thinking: Ability to reason through algorithmic choices, customize for problem constraints, debug systematically

Education & Experience

• MS or PhD in Computer Science, Applied Mathematics, Electrical Engineering, or related field
• Computer Science degree strongly preferred
• Relevant coursework: Algorithms, Machine Learning, Optimization, Software Engineering

Preferred:

• GPU programming (CUDA, performance optimization)
• Parallel computing (MPI, OpenMP, distributed training)
• Bayesian methods (Gaussian processes, uncertainty quantification)
• Active learning and sample-efficient optimization
• Software Engineering
• Experience refactoring legacy code or working with large codebases
• CI/CD, testing frameworks (pytest, unittest, integration testing)
• Design patterns in practice (Factory, Observer, Strategy, etc.)
• Version control best practices (Git workflows, code reviews)
• Performance profiling and optimization
• Domain & Research
• Publications in ML conferences/journals
• Understanding of semiconductor manufacturing or materials science
• Experience with experimental design
• Knowledge of statistical inference from noisy experimental data
• Experience with sparse, noisy, high-dimensional data
• PyTorch/TensorFlow internals knowledge