Machine Learning & Computer Vision Scientist – R&D (Junior/Associate)

Early applied ML/CV experience: 0–3 years applying ML and/or computer vision to real datasets through academic projects, internships, industry roles, or open‑source work, with evidence of hands‑on model development and evaluation.

: Proficiency in Python and familiarity with ML/CV libraries such as scikit‑learn, PyTorch or TensorFlow, and OpenCV; understanding of core ML concepts and basic deep learning; and a collaborative, clear‑communicating working style.

Scientific data and project experience: Exposure to scientific datasets (e.g., high‑content imaging, histopathology, microscopy, behavioral video, assay data) and completed projects, theses, or publications showing applied ML/CV skills with scientific or healthcare relevance.

Technical craft and tooling: Familiarity with training deep learning models on GPUs, use of Git and reproducible workflows, and exposure to data platforms or cloud environments such as Databricks, Azure, or AWS.

We offer a comprehensive benefits package focusing on financial, physical, and mental well-being while encouraging our employees to pursue our purpose! Some highlights include:

Multiple relocation packages

Two weeklong shutdowns (mid-summer and year-end) in the US (in addition to PTO)

8-week parental leave

9 Employee Resource Groups

Annual bonus offering

As the Machine Learning & Computer Vision Scientist (Junior/Associate), you will help drive Elanco’s R&D innovation by implementing and refining ML and computer‑vision models that support faster, better‑informed decisions.

You will work closely with senior scientists and R&D stakeholders to turn proprietary molecular, in vitro, imaging, and digital endpoint data into predictive and classification models for target identification, molecular optimization, ADMET, and digital biomarkers in animal health.

Implement and refine ML/CV models under guidance, developing, training, and tuning models on R&D datasets (molecular, in vitro, imaging, behavioral) in collaboration with senior scientists to align with scientific objectives.

Prepare and manage datasets for modeling by cleaning, transforming, and merging data from multiple scientific sources, running exploratory analyses, and contributing to feature engineering and clear dataset documentation.

Support data collection, annotation, and synthetic data work by helping improve capture and labeling workflows for images, video, and assay data, assisting with annotation guidelines, and evaluating synthetic data and augmentation to improve sparse datasets and model robustness.

Assist with model evaluation and reporting by contributing to train/validation/test design, applying appropriate metrics and error analyses, and documenting methods, assumptions, limitations, and results for review and reuse.