Howard Hughes Medical Institute (HHMI) is investing significantly in AI-driven projects to enhance scientific processes. They are seeking a highly skilled AI Research Engineer to develop methods for adapting pre-trained microscopy vision models and aligning representations across modalities, while collaborating with scientists to integrate these models into various workflows.
Responsibilities :
• Build methods for supervised adaptation of pre-trained microscopy vision models and cross-modality representation learning/ alignment.
• Build robust pipelines that adapt foundation models to specialized microscopy tasks.
• Develop algorithms that align image level embeddings across modalities (e.g., fluorescence ↔ electron microscopy ↔ brightfield ↔ …).
• Use these models for scalable vision tasks, instance segmentation, tracking, classification, and more.
• Utilize probabilistic models to produce uncertainty-aware predictions across scales.
• Lead rigorous model evaluations, implement novel architectures, and ensure all work meets the highest standards of reproducible open science.
• Collaborate with microscopy experts, cellular biologists, neuroscientists, and computer scientists to ensure models can be deployed in large data real-world scenarios.
• Design and execute rigorous experiments to evaluate model performance on a wide distribution of microscopy images and model architectures.
• Collaborate with Scientists at Janelia and the broader academic community to integrate our model into their workflows across a wide variety of vision tasks.
• Collaborate with interdisciplinary teams, potentially mentor junior engineers, and direct or assist in directing the work of others to meet project goals while advising stakeholders on data strategies and best practices.
Qualifications :
Required :
• Masters or PhD degree in Computer Science, Applied Mathematics, Computational Neuroscience, or a related field—or an equivalent combination of education and relevant experience.
• 3+ years of experience fine-tuning spatial transformer networks, contrastive learning, model distillation, RLHF and/or cross-modal alignment methods.
• Familiarity with state of the art vision fine tuning methods, such as low-rank adaptation (LoRA), linear probing etc.
• Strong programming skills in Python, PyTorch, and JAX.
• Familiarity with computational tools in microscopy and connectomics data (Cellpose, CAVE, Flood Filling Networks, Neuroglancer, Zarr).
• Experience with ML model deployment, workflow orchestration, and high-throughput data processing and model training.
• Keen interest to work in a truly interdisciplinary environment and learn about cellular/molecular biology (e.g. transcriptomics) & neuroscience.
• Strong programming skills in Python, PyTorch, and/or JAX are required.
• Knowledge of microscopy data formats and tools such as Zarr and Neuroglancer.
• Ability to reason about neural network behavior from first principles.
• Ability to think critically about model design, understand how architectural choices and regularization affect model behavior, and design rigorous experiments to evaluate models.
• Familiarity with state-of-the-art vision frameworks such as DinoV3, SAM, CellPose, or Vision Transformers.
• Experience working with large biological datasets in scalable GPU-based computing environments.
Preferred :
• Skills in Javascript are a plus.
• Domain expertise in microscopy image analysis is not necessary, but will be highly valued.
Company :
Founded in 1953, HHMI invests in scientists at all career stages who make discoveries that advance human health and our fundamental understanding of biology. Founded in 1953, the company is headquartered in Chevy Chase, USA, with a team of 1001-5000 employees. The company is currently Late Stage.