Senior Multimodal ML Scientist for Autonomous Labs

Genentech, Inc.; South San Francisco (CA); On-site; USD 168,000 - 312,000; Full time

Benefits offered by this job

Discretionary bonus

Job summary

Genentech, Inc. is seeking a Senior Multimodal Machine Learning Scientist to lead hands-on development of autonomous laboratory systems.

The role spans computer vision, multimodal perception, and end-to-end ML pipelines, from data collection to deployment, with emphasis on safety, robustness, and real-time inference across diverse lab instruments. The position emphasizes cross-disciplinary collaboration with scientists, automation engineers, and software teams to translate experimental

Qualifications

• MS/PhD in CS, Data Science, AI, or related field with 3+ years deploying production ML.
• Experience translating frontier AI into biological workflows.
• Strong background in computer vision and vision-language systems with hands-on model training and evaluation.
• Hands-on experience building and deploying multimodal models that fuse visual data with sensor/series data.
• Proven track record deploying production ML systems and developing evaluative pipelines.

Responsibilities

• Develop and fine-tune state-of-the-art vision models for real-time QC in lab cells.
• Integrate camera feeds with time-series telemetry and lab data for multimodal analysis.
• Build predictive models from spectroscopy and plate-reader data to guide experiments.
• Create end-to-end ML pipelines for data collection, labeling, training, deployment, and monitoring.
• Develop agentic pipelines that execute autonomous lab decisions and recoveries.
• Establish robust eval suites to benchmark model and agent safety and accuracy.
• Deploy scalable, low-latency ML inference and monitoring infrastructure.

Skills

Computer Vision

Vision-Language Models

Multimodal Models

ML Pipelines

Eval Pipelines

Agent Frameworks

Education

MS/PhD in CS, Data Science or related

Tools

PyTorch

OpenCV

Torchvision

Job description

Genentech, Inc. is seeking a Senior Multimodal Machine Learning Scientist to lead hands-on development of autonomous laboratory systems.

The role spans computer vision, multimodal perception, and end-to-end ML pipelines, from data collection to deployment, with emphasis on safety, robustness, and real-time inference across diverse lab instruments. The position emphasizes cross-disciplinary collaboration with scientists, automation engineers, and software teams to translate experimental