Senior Software Engineer, Genomics

About this role

About Feanix Bio

Feanix is rebuilding animal breeding from the genome up.

We’re a YC-backed startup using whole-genome sequencing and custom ML models to help dairy farmers make better breeding and herd management decisions. Our technology is genuinely novel: we can sequence a full genome from a single hair at a fraction of traditional industry costs, our models achieve ~90% prediction accuracy on traits where existing approaches sit closer to ~30%, and we’re pioneering farm-specific genomic predictions that turn genetics into practical, actionable decisions.

That technology is translating into real adoption. In a short time, we’ve grown to serve roughly 1% of the U.S. dairy industry, with many customers in the pipeline. We started with dairy because our founders grew up on dairy farms and understand firsthand the problems we’re solving. But genetics is foundational to every agricultural industry, and dairy is only the beginning.

We’re building Feanix with a small, high-caliber team where people have meaningful ownership and work end to end. There are no unnecessary layers and very little room for busywork — just difficult problems at the intersection of biology, data, and software that haven’t been solved before.

If you’re exceptional at what you do and want your work to have a measurable impact on an entire industry, we’d love to build it with you.

About The Role
Feanix’s main product Autopilot is a farm decision system. It tells dairy farmers what to do with every animal in the herd: which cows to breed and with what semen, which to cull, which to sell, and which heifers are worth raising. Those decisions are driven by herd records, lactation models, farm economics, and genomics, with one aim: making each farm as efficient and profitable as possible.
Genomics at Feanix runs from sample to result. We collect hair samples from animals, run our own sequencing process, and impute full genotypes against a reference panel. Those genotypes tell us what each animal is really worth, confirm who its parents are, and help farms avoid inbreeding as they choose which bulls to breed to which cows.
This is a production role, not a research one. Our genomics work supports research, but above all it feeds the decisions that run working dairies. Genotypes don’t make those calls alone: combined with each herd’s phenotypic data (milk, reproduction, health, and lifetime records), they decide which animals to breed, keep, and sell, every week.
The base methods behind these pipelines are strong, and so is the pipeline we’ve built to run it. What comes next is expanding it for much higher volume, tighter accuracy, and lower cost per sample as we grow from 20+ farms to hundreds. And dairy is where we started, not where we stop: the pipeline you build should be ready to carry other species and genomics uses beyond the herd decisions we deliver today.
We're building out genomics as a core capability of engineering, and this is our second genomics hire. You'd partner with our founding genomics engineer, who brings deep knowledge of the genetics and the methods behind them. You bring the production engineering. You’d lead how our genomics pipelines are built and run, taking them from manually orchestrated to fully automated under code, CI, and monitoring, and set the engineering standards for genomics as the team grows. Their domain depth plus your production experience is what makes the science run unattended, observably, and repeatably, every week, at hundreds of farms.
What You'll Own
The genomics team owns everything below together; you’re the one who leads on making it production-grade. The work is continuous: keep making the genomics processing pipeline more automated, more reliable, faster, and cheaper per sample, so that adding a farm adds samples, not engineering work.

•
The genomics pipeline as a production system. Sample → sequence → align → impute → genotype → parentage/trait, scheduled or triggered by new data, with retries, version pinning, and alerting.

•
A sample-state ledger. One authoritative record per sample of where it is (received, sequenced, passed coverage, imputed, called) and, if it stopped, why.

•
Parentage, end to end. Our parentage results already reach farms, built on the same genotypes, sample identities, and compute as the rest of genomics, so the team owns it end to end, from sample to result. You’d move fleet runs onto a schedule with completion and lateness alerts, and finish the readiness work that makes our already-built successor runner the system of record.

•
CI and deploys, in partnership with infrastructure. Our infrastructure engineer designs the CI and deploy path across engineering. You’d work with them to bring the genomics repositories onto it, so every change is tested and every pipeline and workflow version is managed in code and reviewed.

•
Cost and storage. A cost-per-sample view for sequencing compute and storage, and a lifecycle policy for data measured in hundreds of terabytes.

•
Lab and vendor intake. The handoff from our in-house sequencer, outside sequencing labs, and genotyping-chip providers into the pipeline.

•
Reproducible model training. Making breeding-value model training runnable and repeatable, so time goes to methods, not reruns.

You’ll work closely with others who own the pieces on either side. Our founding genomics engineer owns methods and confidence thresholds. You should understand them well enough to debug and push back, not redesign them. Model selection and promotion into breeding decisions, delivery of results into farmers’ herd software, and the platform-wide animal identity key each sit with other engineers. The genomics team owns sample identity and how samples attach to that key.
How We Work
Python end to end, with uv and pytest, on AWS. Genomics runs on a mix of compute chosen per workload: Modal for serverless Python, Nextflow workflows on AWS HealthOmics, AWS Batch, and GPU-accelerated alignment. Data lives in S3. The…