Lead Genomics Engineer for Cohort-Scale Analysis

DIPLOID GENOMICS INC; San Diego (CA); Hybrid; USD 170,000 - 250,000; Full time

Job summary

DIPLOID GENOMICS INC is seeking a Senior Bioinformatics Engineer to design and build scalable, high-performance tools for cohort-scale genome analysis. The role blends software engineering with genomics research to enable reliable research and diagnostic capabilities from complete human genomes.

You will develop reproducible pipelines, apply AI/ML to large cohorts, and work cross-functionally with scientists and clinicians. Hybrid or onsite work may be required.

Qualifications

• MS. or Ph.D. in Bioinformatics, Computational Biology, Computer Science, Genomics, or a related discipline — or equivalent practical experience.
• 5+ years of hands‑on experience (or Ph.D. plus 3+ years) in large-scale genome analysis, including whole-genome and pangenome projects.
• Extensive prior experience in genome research (not limited to human genomes), and a willingness to apply and extend those skills — and learn new techniques — for human‑scale genome analysis.
• Proven ability to scope, design, build, and operate production‑grade, end‑to‑end bioinformatics pipelines with minimal guidance, taking accountability for their correctness, scalability, reproducibility, and performance in high‑throughput and high‑performance computing and cloud environments.
• Deep, current understanding of state‑of‑the‑art bioinformatics algorithms across genome assembly, variant calling, structural‑variant calling, haplotype phasing, and pangenome analysis, with the judgment to select, adapt, and benchmark them appropriately rather than applying them off the shelf — the level of expertise the team can treat as a go‑to resource.
• Strong software engineering foundations: proficiency in Python (and ideally a compiled language such as C/C++, Rust, or Go), version control, automated testing, containerization (Docker / Singularity), and workflow managers (Nextflow, Snakemake, or WDL).
• An independent generalist who thrives in a startup environment — comfortable working with minimal direction across a broad range of tasks, taking ownership of problems from start to finish, and adapting quickly to a fast pace and rapidly changing requirements while prioritizing the most immediate needs.
• A track record of elevating a team by developing others — using prior experience to mentor entry‑level and mid‑level staff toward independent, high‑quality work through teaching, design and code review, and stepping in directly only when necessary — rather than through direct management.

Responsibilities

• Systematically evaluate large cohorts of human genomes across all variant types — SNVs, indels, structural variants, and other complex events — derived directly from personal, de novo genome assemblies, with particular attention to difficult-to-sequence and difficult-to-map regions.
• Develop and apply metrics and quality frameworks to assess the accuracy, completeness, and consistency of variant calls across the cohort.
• High-Performance Cohort Genome Analysis Platform
• Contribute to the engineering work of building a high-performance platform for cohort-scale, complete-genome analysis, and assist with its maintenance and continuing improvement.
• Help keep the platform scalable, reproducible, and efficient as cohort size and data volume grow.
• Drive research and diagnostic applications built on extensive cohorts of complete human genomes, supporting biomarker discovery, missing-heritability studies for complex disease, and oncology applications.
• Collaborate with scientists, clinicians, and cross-functional teams to translate cohort-scale findings into research insight and diagnostic value.
• Apply AI and machine-learning methods to genomics to improve the efficiency of processing and interpreting large cohorts, working closely with peers across the team.
• Explore and evaluate AI approaches that help extract biological and clinical insight from complete-genome cohort data at scale.
• Conduct scientific study and review the most recent literature, and drive toward applications by turning promising methods and findings into practical tools, analyses, and improvements.
• Identify inefficient algorithms or code and improve them when necessary, performing analyses to evaluate and compare alternative approaches on representative data.
• Adopt and adapt new computational technologies and software-engineering tools and practices to keep the platform, methods, and codebase current, efficient, and maintainable.

Skills

Python

C/C++

Docker

Nextflow

Snakemake

WDL

Education

MS/PhD in Bioinformatics, Computational Biology, Computer Science, Genomics

Tools

AWS

GCP

Job description

DIPLOID GENOMICS INC is seeking a Senior Bioinformatics Engineer to design and build scalable, high-performance tools for cohort-scale genome analysis. The role blends software engineering with genomics research to enable reliable research and diagnostic capabilities from complete human genomes.

You will develop reproducible pipelines, apply AI/ML to large cohorts, and work cross-functionally with scientists and clinicians. Hybrid or onsite work may be required.