Associate Principal Scientist, Computational Biologist and Image Analysis Expert

Merck • Cambridge, MA

4d • Hybrid

About The Position

Our company is on a quest for cures and is committed to being the world’s premier, most research-intensive biopharmaceutical company. Today, we’re doubling down on this goal. Our company's Research Laboratories is a true scientific research facility of tomorrow and will take our company's leading discovery capabilities and world-class small molecule and biologics R&D expertise to create breakthrough science that radically changes the way we approach serious diseases.
The Data, AI & Genome Sciences department is looking for a passionate and talented computational biologist with deep expertise in image analysis to join our Translational Genome Analytics research team. In this role, you will apply AI/ML-based analytics to analyze large multi-scale and multi-omics imaging- and functional genomics-based datasets and closely collaborate with a cross-functional team of computational biologists, data scientists, and stakeholders in Discovery Research to drive target and biomarker discovery and drug development efforts. This role will support multiple therapeutic areas with a strong emphasis on Oncology.
The successful candidate will be a scientifically curious team player, strong communicator, and self-motivated learner with previous demonstrated expertise in computational image analysis, experience with multi-omics data integration and functional genomics assays, and an interest in leveraging AI/ML strategies to aid in our interpretation of complex biological data.
This role is based at our company's Research Labs in Cambridge, MA.

Requirements

• In-depth experience with analyzing high-content cellular and/or tissue imaging assays (e.g., Cell Profiler, scikit‑image, OpenCV, etc.).
• Deep experience with computational analysis (e.g., stain normalization, WSI-level classification, segmentation, etc.) of histopathology imaging (e.g., H&E/IHC whole slide images).
• Advanced programming skills with application in imaging (Python) and statistical analysis (R, tidyverse packages).
• Demonstrated ability to distill complex data into interpretable visualizations (e.g., ggplot2, plotly).
• Demonstrated experience with computational analysis and biological interpretation of diverse large-scale experimental datasets from NGS and arrayed screening.
• Skilled at integrating results generated from multiple omics data sources, and biological knowledge bases to customize analytical approaches for discovery research.
• Experience with AWS cloud computing infrastructure (e.g., S3, EBS, EC2, etc) and HPC Linux environments.
• Experience with version control systems, such as Git, and the ability to collaborate on code bases and adapt to and work with existing analytic frameworks.
• Passion for problem solving and continuous learning; applied both to understanding biology and solving technical challenges.
• Self-motivated, proactive, detail-oriented, and independent phenotype supported by references.
• Excellent verbal and written communication skills for cross-disciplinary collaboration.
• Previous experience as full-time computational biologist.

Nice To Haves

• Experience with optical pooled screening (OPS).
• Close familiarity with histology/microanatomy and microscopy readouts.
• Experience with digital pathology.
• Experience with using or developing pipelines with workflow orchestration tools such as Nextflow.
• Hands-on experience with applying AI/ML methods for analysis of image-based biological readouts.
• Interest in identifying novel applications of AI/ML strategies for biological target discovery.
• Experience with and understanding algorithms for DNA-seq, RNA-seq, single-cell RNA-seq and/or functional genomics data.
• Strong publication record.

Responsibilities

• Contribute to multiple stages of drug discovery by interrogating high-throughput functional genomics and cellular profiling assays, including high-content imaging-based screens (e.g., optical pooled screens, cell painting, arrayed CRISPR assays), large-scale NGS-based screens (e.g., pooled CRISPR screens, Perturb-seq), and proteomic datasets.
• Translate biological questions into computational solutions by performing quantitative and rigorous statistical analysis on large-scale in vitro imaging datasets and clinical histopathology images for novel biomarker and target discovery.
• Leverage machine-learning approaches to integrate multiparametric image-derived features with high-throughput phenotypic screens.
• Closely collaborate with a broad variety of stakeholders, including molecular biologists, pathologists, bioinformaticians, and software engineers, and act as a proactive bridge and translator in cross-disciplinary communications.
• Employ best reproducible research and FAIR data practices to generate reusable analysis frameworks and reports to support target identification and validation efforts across therapeutic areas.
• Characterize novel targets coming from genetics, translational and disease pathway exploration, explore target engagement, research mechanisms of action, and provide functional validation of novel drug targets.
• Work with large internal and public biological data sets including Next Generation Sequencing (NGS) data (e.g. RNA-Seq, single cell RNA-Seq, spatial transcriptomics, WGS, CRISPR).

Benefits

• medical, dental, vision healthcare and other insurance benefits (for employee and family)
• retirement benefits, including 401(k)
• paid holidays
• vacation
• compassionate and sick days

What This Job Offers

• Job Type: Full-time
• Career Level: Principal
• Education Level: Ph.D. or professional degree