Staff Data Engineer, Lab Data Platform

Speedrun Talent Network; Boston (MA); On-site; USD 140,000 - 200,000; Full time

Job summary

Asimov is seeking a data platform engineer to own the path from bench to warehouse to model, blending lab insight with software development. You will standardize how our lab captures data and build ingestion tooling that makes the right way the easy way.

Design and run pipelines from instruments and ELN/LIMS into BigQuery and Kernel, ensure data quality, lineage and versioning, and deliver ML-ready datasets and APIs to power KernelAI and our modeling team.

Qualifications

• 8+ years building production data systems and ownership of data platform architecture.
• Strong Python and SQL skills with ability to ship backend services and APIs.
• Experience in biotech wet lab environments and handling messy lab data.
• Ability to turn ambiguous problems into scalable data systems adopted by scientists.

Responsibilities

• Standardize how the lab captures data and define sampling/measurement metadata.
• Own the lab data platform end to end, with ingestion tooling and data lineage.
• Model the biology and processes by linking designs to constructs and measurements.
• Deliver ML-ready datasets and APIs that surface lab results inside Kernel and KernelAI.
• Build reporting and dashboards with scientists to close the data-to-design loop.

Skills

Python

SQL

Data pipelines

Backend services

APIs

Data architecture

Tools

BigQuery

ELN/LIMS

Job description

Asimov's mission is to advance humanity's ability to design living systems. We build mammalian cell lines, genetic parts and lentiviral systems in our Boston lab, and we build Kernel, the model-driven CAD platform that turns that lab's knowledge into software our partners use to design next-generation therapeutics.

We've built a best-in-industry dataset for mammalian cell line development: thousands of antibodies, plasmids, genetic elements, pools and clones, each linked to the measurements that show how they actually performed in the lab. That data already powers Kernel's design recommendations and our predictive models, and it's a big part of why partners choose us.

Now we want to take it to the next level of maturity. That means capturing every instrument’s data from every experiment the same way, at higher throughput, continuously improving in quality and depth of analysis, fully traceable to the designs and conditions that produced it and ready for the next generation of models. We're looking for one person to own that path from bench to warehouse to model: half data engineer, half software engineer, with your feet in the lab.

About the Role:

• Standardize how the lab captures data. Sit with our cell line development, analytics, and molecular biology teams to define how samples, conditions and measurements are recorded, then build the ingestion tooling that makes the right way the easy way.

• Own the lab data platform end to end. Design and run the pipelines that move data from instruments, our ELN/LIMS and bench workflows into our warehouse (BigQuery) and into Kernel, with quality checks, lineage and versioning built in. Embrace FAIR principles in data stewardship.

• Model the biology and the process. Build schemas that link a molecule design to its constructs, the cell pools and clones that carry them, the bioprocess, and every titer, quality, and stability measurement taken along the way.

• Feed the models and the product. Deliver clean, ML-ready datasets to our modeling and computational biology team, and ship APIs and services that surface lab results inside Kernel and to KernelAI, our agentic design assistant.

• Enable the science. Build deterministic and agentic reporting and analysis tools and dashboards side by side with computational and data scientists to close the loop from data back to design input.

About you:

• You have 8+ years building production data systems (5+ for Senior), and you've owned a data platform's architecture, not just its pipelines.

• You write strong Python and SQL, and you're comfortable shipping backend services and APIs, not only batch jobs.

• You've worked in or alongside a biotech wet lab, and you know why lab data gets messy. You'd rather walk into the lab and watch an experiment than guess at requirements.

• You can take an ambiguous, first-of-its-kind problem and turn it into a system scientists actually adopt.

We're a small team where software engineers and biologists share a floor, and your work shows up in real experiments within weeks, not quarters. We value velocity, autonomy and concrete outcomes over process. If you've ever wished lab data just made sense, come build the system that makes it so.

We’re fueled by a vision to transform biological engineering into a fully-fledged engineering discipline. Should you join our team, you will grow with a constantly evolving organization and push the frontiers of synthetic biology. Company culture is key to Asimov, and we believe that our mission can only be achieved by bringing together a diverse team with a mixture of backgrounds and perspectives.