Nomic Bio

• Build core sub-components of our software stack — database schemas, analysis pipelines and new analysis algorithms, cloud infrastructure and related IaC, full-stack web interfaces, machine learning models, and APIs consumed by our own services and by customers. You'll lean on AI coding tools to move quickly, while owning the architecture, review, and correctness. • Design and build agentic backends, skills, and AI-augmented tooling — including LLM-powered workflows and machine-readable interfaces — that let our teams (and our agents) interact safely with the LIMS, data pipelines, and lab automation. Help us figure out where agents create real leverage and where they don't. • Develop improved internal tools for our LIMS, and software for our R&D teams, in order to increase operations and R&D velocity in the lab, including developing and implementing an electronic lab notebooks (ELN) plan tailor fit to our profiling and manufacturing lab operations. • Write modular software that we can use to create efficient analysis pipelines and internal QC tools, making use of existing libraries, open source platforms, and commercial options as best suited to the challenges at hand. • Build better interfaces to the tools that are available out-of-the-box from our robotic lab automation equipment suppliers, and extend these capabilities going forward so as to enable our lab teams to interface with our software stack as seamlessly as possible. • Contribute improvements to the codebase that enable us to further scale up our nELISA decoding and analysis pipelines; write tests and evals, including for AI-generated code and ML/agentic components, integrate the stack with appropriate monitoring and analytics, and set up robust CI/CD when appropriate. • Deploy and scale our data pipelines for processing flow cytometry data into quantitative protein concentrations. This will be done in close collaboration between our Data Engineering and Software Engineering teams. • This role will involve substantial communication and teamwork not just within our software engineering team at Nomic, but also with the broader range of internal users of the LIMS, data portal, and data pipeline software, including customers at times.

About Us Nomic was founded with a simple but ambitious goal: to make biology easier to measure. We’ve developed nELISA , the world’s highest throughput proteomic platform, by tackling some of the toughest challenges in protein profiling through a combination of DNA nanotechnology, high-dimensional flow cytometry, lab automation, and machine learning. Since spinning out of McGill University, we’ve partnered with dozens of top-tier drug discovery groups, including 6 of the top 10 pharma companies, and have profiled over 60 million proteins from more than 400,000 samples to date. Since closing a $42M Series B round, we recently scaled up the platform to meet rapidly growing demand. You can read more about this on our website here. Our state-of-the-art facility is capable of profiling over 2.5 million samples a year, generating 500 million protein assays. We’re a diverse team of engineers, scientists, and problem-solvers who thrive on breaking down difficult challenges using first principles thinking, and we leverage the latest scientific and technological breakthroughs to drive our mission forward. About the Role As our Staff-level Bioinformatics & ML Scientist, you will elevate Nomic’s position as the leader in large-scale proteomics. Your work will set new standards for how proteomic and multi-omics data are analyzed, interpreted, and applied, helping our customers move from raw data to scientific breakthroughs. By enabling new decision-support models, building and expanding our reference datasets, and sharing thought leadership with the broader community, you will help define what’s possible for the field and accelerate discoveries across drug development and biomarker research. You will also ensure Nomic’s customer collaborations deliver high-impact insights and become the gold standard for industry and academia. You will join a cross-functional team and build on existing infrastructure to develop the analysis pipelines, ML models, and product-facing workflows that make proteomic data actionable for customers. Your work will shape the applications layer in the Nomic Portal and support key use cases such as target discovery, perturbation analysis, and translational research. This is a player-coach position, you will mentor and collaborate closely with our engineering, product and data teams as our capabilities grow. What You’ll Be Doing Bioinformatics, ML, and Multi-omics Analysis Build and improve pipelines for proteomic and transcriptomic data: QC, normalization, batch correction, feature engineering, and integration. Develop ML models and analytical methods for target discovery, perturbation and functional genomics analysis, and phenotype classification. Prototype ML-driven approaches and work with engineering teams to productionize them. Scientific Interpretation & Applications Development Interpret multi-omics datasets and connect data patterns to underlying biology. Support analyses involving perturbation screens or functional genomics methods. Define and translate customer analysis needs into specific Portal features and workflows. Customer-Facing Scientific Insights Support customer projects with exploratory and confirmatory analyses. Identify and communicate the insights most relevant to customer decisions. Present data clearly and rigorously in sharable notebooks, presentations, and discussions. Cross-Functional Collaboration & Thought Leadership Work with product, commercial, and scientific teams to define high-impact use cases. Contribute to scientific content that strengthens Nomic’s leadership. What We’re Looking For PhD (or equivalent experience in Bioinformatics, Computational Biology, ML, or a related quantitative field.) Direct experience analyzing proteomics and transcriptomics datasets Experience working with data from target discovery, perturbation, or functional genomics workflows. 5+ years of hands-on experience building bioinformatics or ML pipelines in Python and/or R. Comfortable staying hands-on with coding and analysis while mentoring others. Strong statistical and data-wrangling skills, including QC and normalization. Familiarity with reproducibility and collaborative coding practices. Experience collaborating with engineers, scientists, or product teams. Experience contributing to scientific publications or technical content. Experience with customer-facing scientific work is ideal. Understanding of how pharma and biotech teams evaluate biological data is ideal. Excellent written and verbal communication skills.

• Designing, building, iteratively improving, and fully automating the data pipelines and algorithms we use for processing raw flow cytometry data from our highly multiplexed bead-based assays into quantitative protein measurements. • You will leverage your fundamental knowledge of biosensors, fluorescence data, and bioengineering R&D to act as an expert for the interpretation, and analysis of, nELISA experimental data when challenges arise in R&D and day-to-day Lab Operations. • You will also support R&D and Lab Operations teams through developing additional data support features and algorithms to support the growth of Nomic going forward. • This role will involve substantial communication, teamwork, and attention to detail, especially when identifying and troubleshooting issues related to nELISA data and ensuring we build the right tools, and the right abstractions. • When tooling does not yet exist, you will leveraging your technical and bioscience domain expertise to develop new data analysis pipelines.