Junior Data Scientist — Genomics & Biomarker Analysis

Amelia Hughes

Contract-to-hire · Junior · New_York

This role is no longer accepting applications

Similar open roles you can apply to now:

About the role

We are an early-stage genomics company. We are using long-read sequencing and machine learning to identify novel biomarkers for early cancer detection from liquid biopsy samples. We have twelve people and two years of runway after our seed round. We are not a normal place to work. The science is hard, the timelines are uncertain, and the people here have all made a deliberate choice to work on something ambitious and difficult rather than something comfortable. We are also a place where a junior data scientist will get exposure to problems and responsibilities that would take years to reach at a larger organisation. We are hiring a junior data scientist to join our bioinformatics and ML team — currently three people. You will work on the statistical analysis of sequencing data and on the ML models we are developing to distinguish true cancer signal from the noise in cfDNA data. This starts as a 6-month contract because we have a specific analytical programme to complete in that period. Our strong intention, contingent on the science and funding going as planned, is to convert to a permanent role at the end of the term.

Responsibilities

Analyse cfDNA sequencing data from our current clinical sample cohort to characterise signal-to-noise ratios across cancer types
Build and evaluate ML classification models for distinguishing cancer signal from sequencing artefact and germline variation
Contribute to the development of our biomarker feature engineering pipeline
Maintain analysis reproducibility — every experiment documented and version-controlled so that results can be replicated and extended by other team members
Prepare data analysis sections of our scientific reports for our clinical partners and seed investors

Requirements

1–2 years of data science experience or a strong quantitative degree (bioinformatics, statistics, computational biology, or related) with hands-on data project work
Python for data analysis and working with genomic data formats — experience with BioPython, pandas-based genomics workflows, or equivalent is welcome
R for statistical analysis — our bioinformatics team primarily works in R and you will be collaborating on their analysis
SQL for working with our sequencing run database and sample metadata store
Statistics: understanding of statistical significance in the context of high-dimensional genomics data, multiple testing correction, and the ability to reason carefully about what a small sample of clinical data can and cannot tell you
NumPy and Scikit-learn for building the baseline ML models we use to evaluate feature engineering approaches before moving to more complex architectures

Benefits

$72,000 – $88,000 annualised contract rate — permanent salary to be discussed at conversion
6-month contract with strong intention to convert
Fully remote with monthly in-person science days at our Cambridge, MA lab
Access to long-read sequencing data at a sample scale you would not reach in most early-career positions
The chance to be part of something where the science question actually matters — early cancer detection is a hard problem worth working on