Machine Learning Engineer

About the Role

We are seeking an ML Engineer who can design and implement AutoML pipelines and agentic systems that support real-world chemical and materials-science projects across multiple data modalities. You will work closely with domain experts, software engineers, and research teams to build reliable, scalable, and production-ready ML workflows.

This role is well-suited for someone who enjoys hands-on ML engineering, building automation pipelines, and working with scientific datasets.

Key Responsibilities:

Build, maintain, and optimize AutoML pipelines for chemical and materials-science datasets (tabular,

time-series, spectral, imaging, etc.).

Develop agentic ML systems that can orchestrate workflows, run experiments, and support scientific

decision-making.

Implement end-to-end ML workflows using Python, PyTorch, scikit-learn, and model-management

tools.

Use MLflow, Prefect, or similar platforms for experiment tracking, orchestration, and deployment.

Integrate langgraph-based components into ML automation pipelines.

Work with domain specialists to preprocess, clean, and analyze scientific datasets.

Ensure reproducibility, robustness, and performance of ML solutions.

Contribute to internal libraries, automation scripts, and engineering best practices.

Required Skills:

Strong proficiency in Python and ML engineering fundamentals.

Experience with PyTorch and/or scikit-learn for model development.

Familiarity with MLflow, Prefect, or similar tools for tracking and orchestration.

Understanding of how to structure and automate ML pipelines.

Exposure to scientific datasets (chemistry, materials, physics, bio, spectroscopy, images, etc.).

Ability to write clean, modular, and well-documented code.