Research Intern, Machine Learning

onepot • South San Francisco, CA

2d • Onsite

About The Position

onepot is automating chemistry by combining AI and advanced robotics. Its goal is to create a self-improvement loop in which AI systems design experiments, robotic systems execute them, and the resulting data improves future models. The company brings together ML engineers, chemists, computer scientists, and hardware engineers to build chemistry models, many of which are state-of-the-art and trained on proprietary datasets. Models are used internally in real workflows, with a feedback loop between usage, data, and model training.

In this role, you will help train the next generation of chemistry models and enable the synthesis of previously inaccessible molecules. The work spans the full modeling stack: collaborating with lab staff on data acquisition, training models of different types and sizes, and deploying models directly into experimental workflows. You will also build and help maintain model-training infrastructure and abstractions, including data pipelines and system tasks such as parallelism strategies and quantization. The role aims to develop models with superhuman chemistry intuition and experimental capabilities.

The position is fully in person at onepot’s South San Francisco lab. It does not involve lab work, although some projects may require understanding lab workflows. The role requires the ability to work safely in an active chemistry laboratory and around scientific equipment, and to work extended hours and weekends as necessary.

Requirements

• Strong fundamentals in machine learning and a deep understanding of modern empirical and experimental ML.
• Experience developing novel model-training techniques or working with novel tasks or datasets.
• Familiarity with PyTorch or other machine-learning frameworks.
• Knowledge of basic machine-learning theory.
• Enthusiasm for working across the machine-learning stack, including data, training, inference, and deployment.
• Comfort working across disciplines and learning unfamiliar technical areas as needed.
• Strong written and verbal communication skills.
• Curiosity and excitement about chemistry.
• A strong bias toward building, testing, and learning from real systems.
• Ability to work extended hours and weekends as necessary.
• Ability to work safely in an active chemistry laboratory and around scientific equipment.

Nice To Haves

• Background in a deeply quantitative field; experience training machine-learning models is ideal.
• Experience in a startup, research group, competition team, or another environment involving significant ownership and limited resources.
• Experience training LLMs, particularly mid-training and post-training.
• Experience with machine-learning systems, including scaling, kernels, or parallelism.
• Familiarity with chemistry models such as retrosynthesis or mass-spectra modeling, or with cheminformatics.
• Experience with active learning or other techniques suited to low-data regimes.

Responsibilities

• Help train the next generation of chemistry models.
• Work with lab staff on data acquisition.
• Train models of different types and sizes.
• Deploy models directly into experimental workflows.
• Build and help maintain infrastructure and abstractions for training diverse models, including data pipelines and systems for parallelism and quantization.

What This Job Offers

• Job Type: Full-time
• Career Level: Intern
• Education Level: No Education Listed