ML Research Engineer, Foundation Models (Senior / Staff / Principal)

Genesis Therapeutics; San Mateo (CA); On-site; USD 180,000 - 260,000; Full time

Job summary

Genesis Molecular AI is seeking an ML Research Engineer to bridge fundamental ML research and production-grade systems, focusing on foundation models for molecular science. You will collaborate with ML researchers, computational chemists, and drug discovery scientists to translate cutting-edge ideas into scalable pipelines, pretraining, and deployment-ready models that power real discovery programs.

Positions are available at Senior, Staff, and Principal levels, with a strong emphasis on code

Qualifications

• 2+ years industry experience building complex ML systems.
• Deep expertise in scalable foundation models, pretraining/posttraining, and related systems.
• Strong coding skills across the ML stack: Python, PyTorch, distributed training.

Responsibilities

• Drive the R&D and scaling of foundation models.
• Implement, optimize, and build production-ready models from research prototypes.
• Optimize performance of large-scale ML systems, incl. distributed training and GPU optimizations.
• Bridge ML and computational chemistry workflows to deploy models into drug discovery pipelines.
• Own end-to-end experimental lifecycle with rigorous analysis to guide next steps.
• Collaborate with researchers and engineers to integrate models into the discovery platform.

Skills

Foundation models

Python

PyTorch

Distributed training

Code quality

Tools

Pearl

Git

CUDA

Job description

ML Research Engineer, Foundation Models

About the Team

Join a world-class team at the forefront of AI and biochemistry. At Genesis Molecular AI, we’re a tight-knit team of proven deep learning researchers, software engineers, and drug discovery pioneers.

Our shared mission is nothing short of revolutionary: to forge the next generation of AI foundation models that unlock new therapies for patients with severe diseases. We conduct fundamental research at the intersection of machine learning, physics, and computational chemistry, pushing the boundaries of each field.

The Genesis AI team is building the engine for this revolution. We develop large-scale generative models trained across the full spectrum of molecular data, supported by extensive compute infrastructure and simulation pipelines.

The work sits at the intersection of machine learning research, structural biology, and computational chemistry, requiring deep technical rigor and strong interdisciplinary collaboration.

About the Role

This role is for a highly skilled ML Research Engineer who thrives at the intersection of fundamental research and production-grade engineering.

As a core member of the Genesis AI team, you will serve as the engineering pillar for inventing, scaling, and shipping our next generation of foundation models for molecular science.

You will partner closely with ML researchers, computational chemists, and drug discovery scientists to translate cutting‑edge model ideas into systems that power real drug discovery programs.

Your work may involve:

• Scaling model pretraining pipelines
• Advancing reinforcement learning or post-training systems
• Optimizing performance of large molecular models
• Bringing structure prediction models like Pearl into production environments used by chemists and drug programs

This role requires someone who can bridge ML and computational chemistry, translating between disciplines and helping teams move quickly from research insight to deployed capability.

We are looking for someone who can own problems end-to-end, in a fast-moving research environment, translating novel ML ideas into systems that scientists can use in active discovery programs.

Positions are available at various levels of seniority: Senior, Staff, and Principal.

You Will

• Drive the R&D and scaling of our foundation models, taking ownership of the engineering and experimentation for key research initiatives.
• Make cutting‑edge foundation model research a reality at scale. Implement, optimize, and build novel foundation models from the initial research prototypes to high-performance production models.
• Optimize performance of large-scale ML systems, including distributed training, inference efficiency, and GPU-level optimizations where necessary.
• Constantly engage with deep learning literature, building upon novel architectures and training methods to create new capabilities.
• Bridge machine learning research and computational chemistry workflows, working closely with computational chemists, structural biologists, and medicinal chemists to ensure models translate effectively into real drug discovery programs.
• Help productionize Pearl and related structure prediction models, enabling reliable deployment and integration into Genesis’ internal and partner drug discovery pipelines.
• Own the experimental lifecycle with scientific rigor. You’ll design experimental plans, own their execution on our large-scale compute infrastructure, and drive the deep analysis of results to inform the next research cycle and to validate most promising approaches.
• Ship state-of-the-art models to production,
• Collaborate intensely. Work closely with the broader team to integrate your models into our drug discovery platform.
• Mentor and guide other researchers and engineers, fostering a culture of high-quality code, rigorous experimentation, and continuous innovation.
• Contribute to the global research community by publishing some of your work and representing Genesis at top tier AI/ML conferences and workshops.

Who You Are

• 2+ years industry experience of building complex ML systems.
• A research engineer with deep ML rigor. You have deep expertise in building scalable, high-performance foundation models, pretraining, and posttraining methods, and systems around them.
• A builder who ships. You write clean, high-performance code and are comfortable working across the ML stack (Python, PyTorch, distributed training systems). You have demonstrated experience translating research into working systems quickly.
• An expert in modern ML engineering. You understand the mathematics and systems behind modern ML methods. You can design, optimize, and implement novel modeling approaches.
• Experienced in training models at scale. You understand distributed training, large-scale datasets, and performance optimization