Applied ML Scientist - Active Learning

Job Responsibilities

• Lead the design and execution of optimization and active-learning campaigns across chemistry, formulation, and process development.
• Collaborate with R&D and manufacturing on framing optimization problems with design spaces, decision variables, objectives, and hard and soft constraints.
• Design and coordinate sequential experiment campaigns using Bayesian optimization and active learning, accounting for operational variabilities and constraints.
• Select and maintain surrogate models for acquisition, using model uncertainty to drive the search and respecting each model's domain of validity.
• Drive closed-loop optimization that connects surrogate models to experimentation, with emphasis on decision quality, exploration versus exploitation, and actionable recommendations.
• Partner with ML engineers, software engineers, and process engineers to deploy and monitor optimization systems.
• Explore and adopt emerging ML methods, including LLM and agentic approaches, to advance optimization.
• Communicate methods, results, and their limitations clearly to technical and non-technical audiences.

Minimum Qualifications

• Bachelor's degree in Computer Science, Data Science, Statistics, Operations Research, or a related field, with substantial relevant experience in ML modeling or optimization experience for chemistry, formulation, process, or manufacturing problems.
• 7+ years experience.
• Demonstrated expertise in Bayesian optimization and Gaussian processes, including kernels, acquisition functions, and batch, multi-objective, and constrained settings.
• Experience designing and running experiment campaigns or closed-loop optimization.
• Experience in applied statistics and uncertainty quantification, with emphasis on calibrated posteriors that drive acquisition.
• Strong Python skills and experience with mainstream Python-based ML and Bayesian optimization frameworks and tools.
• Active use of AI-assisted coding and other AI tools in daily work, with familiarity with emerging ML methods including LLM and agentic approaches.
• Strong communication, collaboration, and stakeholder management skills for working with R&D, manufacturing, and business teams.

Preferred Qualifications

• Master's degree in Computer Science, Data Science, Statistics, Operations Research, or a related field.
• Experience with active learning and physics-informed approaches for optimization in chemical synthesis, formulation, or process development.
• Experience working with manufacturing, process, quality, or plant data, including issues such as batch-to-batch variability, raw-material variability, model drift, and changing operating conditions.
• Familiarity with ML engineering core tasks and techniques, such as data and optimization pipelines, model deployment, and MLOps.
• Knowledge of chemistry ML core areas such as cheminformatics, molecular representation, predictive modeling, and chemistry foundation models.