Senior Deep Learning Researcher

E Ink is the originator, pioneer, and commercial leader in ePaper technology. Based on technology from MIT’s Media Lab, E Ink has transformed and defined the eReader market. Its Electrophoretic Display products make it the worldwide leader for ePaper. The company’s corporate philosophy aims to deliver revolutionary products, user experiences, and environmental benefits through advanced technology development.

The Deep Learning Center at E Ink is seeking a Deep Learning Researcher to develop and improve product development and research of electrophoretic display technology. Your role will be to use and develop cutting-edge deep learning models to guide materials discovery and display design. This work will take place in a rapidly growing team developing new processes to advance materials discovery and improve mass-produced product performance.

Responsibilities

• Develop and evaluate novel deep learning models for complex physical and chemical systems in advanced materials and display technologies.
• Formulate and test theoretically grounded hypotheses about model behavior and representation.
• Build pipelines for experimental data processing, training, and evaluation.
• Lead inverse design and model-based discovery efforts using Bayesian optimization, diffusion models, or related methods.
• Collaborate with scientists to integrate domain knowledge into deep learning architectures and interpret results.
• Create tools that make models and predictions transparent and usable.
• Promote data quality, reproducibility, and experimental lineage across projects.

Qualifications

• Ph.D. (or exceptional M.S. + 4 years’ experience) in Physics, Applied Math, Computer Science, Electrical Engineering, or related field.
• Demonstrated research experience in deep learning with a track record of innovation.
• Proficiency in Python and major ML frameworks (e.g., PyTorch, TensorFlow, JAX).
• Strong mathematical and problem-solving ability.
• Effective collaborator with excellent communication skills and scientific curiosity.

Preferences

• Experience designing custom architectures, meta-learning systems, or model-based optimization.
• Knowledge of model efficiency techniques (pruning, quantization, distillation).
• Familiarity with inverse design, Bayesian optimization, or generative models.
• Knowledge of colloid science, soft-matter physics, or chemical modeling.

Benefits

• Competitive total compensation package
• Medical, dental, and vision coverage starting on the first day
• Company 401K match
• 20 PTO days
• Generous sick leave policy
• Casual day-to-day work environment
• Hybrid/flexible work environment (for some positions)

Pay

The annual base salary range for this position is $130,000 to $160,000, not including any variable pay. The total compensation package may include performance-based incentives, discretionary bonuses, and other variable pay components.