Bioinformatics Data Engineer

Responsibilities

• Source & Acquire Biological Data - Identify, evaluate, and obtain high-quality bioinformatics datasets from public and partner sources (e.g., NCBI, PubChem, ENCODE,UniProt etc.) to support research and model development initiatives.
• Deeply Understand Complex Datasets - Develop a comprehensive understanding of biological datasets, including data structures, schemas, metadata standards, entity relationships, and underlying biological context to ensure accurate interpretation and usage.
• Design & Implement Data Processing Pipelines - Develop robust preprocessing scripts and scalable data transformation workflows using Python, R, and relevant Tools. Leverage AI-assisted tools where appropriate to process, clean, normalize, and integrate complex biological data for foundation model training.
• Structure & Standardize Biological Data - Organize heterogeneous datasets into well-defined, interoperable formats aligned with internal infrastructure requirements and downstream AI training pipelines.
• Bioinformatics Data Analysis - Perform exploratory and statistical analysis of genomic, transcriptomic, proteomic, and other multi-omics datasets to assess data quality, uncover biological patterns, and generate insights that inform model development. Apply appropriate computational and statistical methods to validate assumptions and support downstream AI training and evaluation.
• Build Data Products - Create production-ready data assets, including standardized datasets, curated releases, dashboards, analytical reports, and technical documentation to enable efficient research and model evaluation.
• Ensure Data Quality & FAIR Compliance - Curate, annotate, validate, and standardize public and partner datasets in alignment with FAIR (Findable, Accessible, Interoperable, Reusable) principles, ensuring long-term usability and reproducibility.
• Collaborate Cross-Functionally - Partner closely with research scientists and ML engineers to translate biological research needs into scalable data engineering solutions that support AI model training and evaluation.
• Knowledge Sharing & Documentation - Contribute domain expertise by documenting data methodologies, maintaining clear technical documentation, and sharing biological data insights across teams.

Qualifications

• Educational Background: Bachelor’s or Master’s degree in Bioinformatics, Computational Biology, Computer Science, or a related field with a heavy focus on the life sciences.
• Biological Data: Deep, hands-on familiarity with multiple biomedical data modalities (e.g., genomics, transcriptomics, spatial omics, protein structure, biomedical imaging, clinical/phenotypic data, etc.).
• Biological Tools: Familiar with Bioconda,Biopython,Bioconductor, samtools,bamtools,bcftools,gffutils etc.
• Scripting & Tooling: Strong programming skills in Python (Pandas, NumPy) and proficiency with standard bioinformatics workflow managers and tools (e.g., Ray, Kubeflow).
• Engineering Handoff: Experience writing clean, modular code that can be easily picked up by core data engineers for optimization in cloud environments (AWS/GCP/HF) and containerized setups (Docker).
• AI/ML Awareness: A solid understanding of machine learning workflows and how biological data must be formatted and batched for deep learning frameworks (e.g., PyTorch).