Scientist / Senior Scientist, Multimodal AI
Core
Design and build high-performance, scalable AI solutions that unify high-dimensional biomedical imaging with molecular and language data to create predictive models mapping across biological domains.
Role type
Senior Scientist, Multimodal AI (IC)
Builds
Production-ready machine learning models and pipelines for biological data analysis
Domain
Biotechnology / Computer Vision / Multimodal AI
Deliverable
production ML models
Required skills
Vision Transformers, U-Nets, Self-Supervised Learning, PyTorch Distributed, DeepSpeed, Jax, Python, large-scale data management
Preferred skills
Multimodal Fusion (image embeddings with transcriptomic/proteomic data), cloud-native AI tools (AWS/GCP, Kubernetes, Docker), MLOps workflows, handling noise and sparsity in biological data
Technologies
PyTorch, DeepSpeed, Jax, AWS, GCP, Kubernetes, Docker
Responsibilities
Design, code, and train large-scale foundation models (Vision Transformers, Multimodal LLMs) embedding spatial data; Implement cross-domain mapping and fusion strategies for heterogeneous biological datasets; Build and manage high-performance ML pipelines for petabyte-scale image repositories and multi-omics streams; Collaborate with experimental scientists and software engineers to translate biological complexity into performant code and distributed systems
Seniority
Senior, hands-on IC
