Data Infrastructure Engineer

Glyphic Biotechnologies • Berkeley, CA

18h • Hybrid

About The Position

At Glyphic Biotechnologies, we plan to create the protein revolution for which scientists and researchers have been waiting. We are developing a massively parallel, single-molecule proteome sequencing platform that will transform life science discovery and usher in a new era of insights into human biology and disease. To date, we have raised >$80M from venture partners and non-dilutive grant funding to achieve our vision of next generation proteome sequencing. What we are looking for in you We are looking for a Data Infrastructure Engineer to design, build, and maintain the data systems that connect our nanopore sequencing instruments to analysis and insight. Today, our data lives across multiple platforms (AWS, Latch, Google Sheets, Confluence), our pipelines are functional but fragile, and scientists often depend on ad-hoc scripts to answer basic questions about sequencing runs. You will change that. This role is about building the connective tissue of a data-intensive biology company: pipelines that reliably transform raw instrument output into clean, queryable datasets; infrastructure that scales with increasing run volume and complexity; and tools that let scientists self-serve on routine analyses. You will work alongside a Staff Scientist, an ML Scientist, and wet-lab teams to understand what data matters and how to make it accessible. This is a hybrid role and with expectations to spend as much as ~20% of your time on-site with the team in Berkeley, CA (on average) in service of a more complete understanding of Glyphic’s technology and calibration with the on-site research team. This role will require some flexibility for additional collaboration as projects require.

Requirements

• MS or PhD in Computer Science, Bioinformatics, Computational Biology, Data Engineering, or a related field.
• 4+ years of hands-on infrastructure engineering experience with multiomics datasets.
• Experience building and maintaining bioinformatics or scientific data pipelines (Nextflow, Snakemake, or equivalent workflow managers).
• Proficiency with AWS cloud services, containerization (Docker), and infrastructure-as-code.
• Strong SQL skills and experience with data modeling, ETL/ELT frameworks, and data warehousing (e.g., PostgreSQL, DuckDB, BigQuery, or Snowflake).
• Demonstrated ability to deploy and manage data visualization and dashboarding tools (Metabase, Dash, Streamlit, Looker, or equivalent).
• Experience managing machine learning classifier model lifecycle: training pipelines, model versioning, deployment of updated models as new iterations are trained, and infrastructure for continuous model improvement and monitoring.
• Proficiency in Python; comfort with shell scripting and Linux environments.
• Navigates complex team dynamics, partnerships, and challenges with creativity and logic.
• Operates with adaptability, urgency, and flexibility in evolving environments, thriving in ambiguity.
• Drives work forward without needing to be asked, taking responsibility for outcomes rather than tasks.
• Treats obstacles as problems to be creatively solved, not reasons something can’t be done.
• Applies sound judgment to the best available information, testing, learning, and iterating.
• Shares early and directly when assumptions change, results are unclear, or timelines are at risk.

Nice To Haves

• Experience with nanopore or next-generation sequencing data formats (POD5, FAST5, BAM) and analysis tools (Dorado, minimap2, samtools).
• Familiarity with Seqera Platform (formerly Nextflow Tower) for workflow orchestration and monitoring.
• Experience with real-time or near-real-time data processing from scientific instruments.
• Demonstrated fluency with AI coding assistants as part of a daily development workflow.
• Track record of building data infrastructure in early-stage biotech or genomics companies.

Responsibilities

• Data Pipelines & Automation Own and extend end-to-end Nextflow pipelines on AWS (Seqera Platform) that process nanopore sequencing output: basecalling (Dorado), amino acid calling, signal alignment, and ML-based amino acid classification.
• Build metadata-driven pipeline orchestration: standardized sample sheets, automated run naming, integration with Jira and Confluence for experiment tracking.
• Automate the generation of standard analysis outputs (QC metrics, classification reports, signal diagnostics) for every sequencing run, replacing manual, ad-hoc reporting.
• Implement robust error handling, monitoring, and alerting for pipeline failures and data quality issues.
• Data Modeling & Storage Design and implement a data model and schema for nanopore sequencing data: raw signal, basecalls, classification results, experimental metadata, and QC metrics.
• Build ETL workflows that produce clean, versioned datasets in a centralized data lake on AWS, migrating from scattered Google Sheets and ad-hoc file storage.
• Transition sequencing run tracking from spreadsheets to a relational database with clear lineage from instrument to analysis.
• Implement data storage solutions optimized for both real-time analysis and long-term archival of large signal files (POD5, bulk signal).
• Visualization & Self-Serve Analytics Deploy and maintain data visualization tools (dashboards, interactive browsers) that allow scientists to independently explore sequencing metrics: yields, classification accuracy, plate-level comparisons, signal quality trends.
• Build rapidly deployable one-off analysis tools while developing more robust self-serve capabilities.
• Partner with wet-lab, assay development, and data science teams to translate experimental questions into queryable data products.
• Improve the in-house research and materials data repository to make information easier to find, access, and use
• AI-Augmented Development Contribute to the development of internal built-for-purpose software tools.
• Leverage AI coding tools (Claude Code, Copilot, etc.) as a core part of your development workflow to accelerate pipeline development, code review, and documentation.
• Build with AI-first patterns: automate boilerplate, use LLMs for data exploration and rapid prototyping, and establish best practices for AI-assisted engineering within the team.
• Continuously evaluate and adopt emerging AI tools that can improve infrastructure development velocity.

Benefits

• Employee Stock Option Plan
• 100% Health Plan Coverage for Employees & Dependents (Medical, Dental, & Vision)
• Employer Retirement Contributions to 401(k)
• Generous Paid Time Off
• Paid Maternity and Paternity Leave
• Health & Wellbeing Program
• Office Snacks and Beverages
• Regular Team Bonding Activities

What This Job Offers

• Job Type: Full-time
• Career Level: Mid Level