Role Summary

Prime Medicine is seeking an AI & Informatics Engineer to join our AI Foundry and support our pipeline delivery.  This includes designing and building the data and computational infrastructure that powers our prime editing programs. This role spans laboratory informatics, NGS pipeline development, and AI-enabled tooling, giving the right candidate a direct line from the work they do to the therapies we develop. You will partner closely with research scientists, computational biologists and technical development professionals, turning raw data into reliable scientific insights, and building automation and AI capabilities that let teams work faster and smarter.

Our ideal candidate brings strong software engineering fundamentals, hands-on NGS pipeline experience, a practical understanding of modern AI frameworks, and the biological intuition to translate scientific needs into working systems. Equally welcome are candidates who entered this space from the life sciences side and have built serious software skills along the way.

This is an action packed and dynamic role where the successful candidate will be involved in multiple programs and activities, so excellent organizational abilities, communications and strong collaboration are critical. The ideal candidate thrives when working in a fast-paced environment, working with purpose, and making an impact for patients.

Key Responsibilities

NGS Pipelines and Data Infrastructure

• Design, develop, and maintain scalable bioinformatics pipelines for NGS data analysis, including amplicon sequencing for on-target editing quantification, using Nextflow and Docker to ensure reproducibility.
• Build and maintain data infrastructure connecting NGS instruments, electronic laboratory notebooks (e.g., Benchling), data repositories, and AWS cloud compute, including automated data ingestion, scalable storage, and provenance tracking.
• Build APIs, MCPs, dashboards, and other internal tools that expose genomic data and analytical capabilities to scientific and cross-functional teams.

Laboratory Informatics

• Support implementation and ongoing development of laboratory informatics systems, including data ingestion from key instruments and integration with laboratory data platforms such as Benchling.
• Support vendor relationships and delivery outcomes for external collaborators, driving requirements, managing implementations, and ensuring high-quality delivery.

AI-Powered Tools and Automation

• Build AI-powered and agentic capabilities that automate routine work, support scientific reasoning, and improve how data and knowledge flow across the organization.
• Develop reusable platform components for retrieval, orchestration, and model interaction, with human-in-the-loop workflows that make AI systems transparent and practical for scientific users.
• Identify and address automation opportunities and scalability bottlenecks across research and operational workflows.

Engineering Practices

• Write production-grade code using Git-based workflows, peer review, testing, CI/CD, and documentation best practices; convert research prototypes into robust, maintainable software.
• Build integrations between internal tooling and third-party platforms to support evolving scientific and operational needs.
• Participate in cross-functional projects spanning lab operations, software engineering, and bioinformatics; recommend best practices, system architectures, and design patterns.
• Perform code reviews and contribute to documentation of engineering and cross-functional practices.

Qualifications

Required

• BS with 5+ years or MS with 3+ years of industry experience in Engineering, Bioinformatics, Data Sciences, or a related field. Candidates with biotech or life sciences with substantial software experience are strongly preferred.
• Strong Python development; proficiency with Nextflow (or comparable workflow tools), Docker, AWS, Linux/Unix, and Git.
• Experience developing and deploying bioinformatic data infrastructure, particularly NGS analysis pipelines.
• Experience implementing or integrating laboratory informatics systems, preferably including Benchling.
• Experience developing and maintaining production-grade APIs and SDKs, and rolling out software tooling across an organization.
• Familiarity with LLM frameworks and practical judgment about where agentic approaches add genuine value.
• Track record of shipping software that scientific or technical users adopt and rely on.

Preferred

• Experience building and deploying AI-powered tools or agentic systems in production or research settings.
• Familiarity with gene editing applications (CRISPR, base editing, or prime editing), including amplicon-seq workflows and tools such as CRISPResso.
• Familiarity with relational databases and data visualization tools (e.g., Plotly Dash, Streamlit, Spotfire).
• Experience in a GxP or regulated software environment (21 CFR Part 11, GAMP 5).
• Experience owning vendor relationships and delivery outcomes for external collaborators in laboratory informatics contexts.

Why This Role

Prime editing is a precise technology, and that precision depends on strong informatics, software, and scientific infrastructure. If you believe that better systems, better automation, and better access to data can translate into safer and more effective therapies, this is the right environment. You will build tools that directly shape how Prime generates, analyzes, and acts on scientific data, while helping lay the foundation for programs to come.