SENIOR DATA SCIENTIST - Python

Job description

**Job Description: Lead Bioinformatics Engineer (Multi-Omics & AI Platform) ? C3/C4** - **Role Summary** We are hiring a **Lead Bioinformatics Engineer** to drive architecture and engineering for an enterprise-scale **Multi-Omics & AI platform**. This is a **systems and platform-building role**, focused a **production-grade data harmonization engine** that transforms fragmented omics data into **ML-ready feature stores**. - **Key Responsibilities** **1. Multi-Omics Data Platform Architecture** - Building **automated harmonization engine** for multi-modal data (genomics, transcriptomics, proteomics, metabolomics) - Develop scalable ETL pipelines to ingest and standardize formats (**FASTQ, BAM, VCF, H5AD, MTX, GCT**) - Architect **ML-ready feature stores** using optimized formats (Zarr, Apache Arrow, TileDB) - Define **3-tier data models** (Dataset, Sample, Feature) linking clinical and molecular data - Implement **ontology mapping** using standards (Ensembl, HUGO, NCBI) - Embed **batch correction & normalization** (e.g., ComBat, Harmony) **2. Pipeline Engineering & MLOps** - Build **production-grade pipelines** for RNA-seq, WGS, and proteomics - Scale data processing on **cloud (AWS preferred: S3, EC2, Batch, Athena)** - Implement reproducible workflows using **Nextflow / Snakemake + Docker/Singularity** - Design **high-performance APIs (Python/R)** for data access and model consumption - Leverage **data lake/lakehouse architectures** (Iceberg, Delta Lake) **3. AI & Data Governance Leadership** - Translate biological problems into **ML-ready datasets and features** - Define **data validation, contracts, and quality checks** - Implement **CI/CD and data quality frameworks** (Great Expectations, Pydantic) - Ensure **data integrity and prevention of bias/data leakage** in AI models **Required Qualifications** 1. **Experience** - Master?s/PhD in **Bioinformatics, Computational Biology, Computer Science**, or related field - **5+ years**? experience in bioinformatics data engineering or platform development - Proven experience building **production-grade data platforms / data lakes for ML** - Hands-on experience with **multi-omics integration (=3 modalities)** - Exposure to **AI/ML pipelines (deep learning, embeddings, LLMs in biology)** 1. **Technical Skills** - Strong expertise in **NGS data processing (WGS, WES, RNA-seq, single-cell etc)** using tools like **GATK, BWA, SAMtools, STAR, Kallisto** and frameworks such as **Scanpy, Seurat, Bioconductor, AnnData** etc - Deep understanding of **variant calling, gene expression analysis, pathway analysis, and single-cell data workflows etc** - Proven experience in **bioinformatics ETL, data harmonization**, and processing **large-scale multi-format omics datasets** - Hands-on with optimized data structures like **AnnData/H5AD, Zarr, Apache Arrow, TileDB**, including **sparse matrix handling** - Experience building **scalable scientific data platforms/data lakes** on **AWS (S3, EC2, Batch, Athena)** with **Delta Lake / Iceberg** - Strong in **workflow orchestration (Nextflow/Snakemake)**, **containerization (Docker/Kubernetes/Singularity)**, and **CI/CD automation** - Proficient in **Python (Pandas, NumPy, Scikit-learn)** with exposure to **PyTorch/TensorFlow** for ML integration - Experience in creating **ML-ready datasets, feature engineering pipelines**, and ensuring **data validation (bias, leakage, quality checks)**