Data Science Contractor

An AI-driven protein engineering company developing novel protein therapeutics across a wide range of diseases is looking to add a Data Science Contractor to their team for the next 12 months.
In this contract role, you will support experimental programs by delivering clean, reproducible analyses of biological data. You will partner closely with experimental scientists to understand assay design, wrangle multi-assay datasets, build decision-grade plots and summaries, and translate results for audiences from bench scientists to leadership. Your work will directly support experimental decision-making and generate high-quality datasets for model training (GenAI) for the design of novel synthetic biomolecules.

You thrive in an early-stage start-up environment where you can leverage your agility and expertise to deliver high-quality results. You are naturally curious and excel when working collaboratively to solve tough problems. You enjoy turning noisy experimental readouts into clean, decision-ready analyses for scientists and leadership.

Required Skills:

• Master’s degree in relevant technical discipline with limited prior industry experience or bachelor’s degree in relevant technical discipline with 2+ years of industry experience.
• 1–3 years’ experience analyzing experimental/biological datasets (industry, startup, or academic lab).
• Ability to understand experimental context (read protocols, interpret assay outputs) and partner effectively with experimentalists.
• Advanced skills in Python data stack: pandas, numpy, data viz, Jupyter workflows.
• Solid grasp of EDA and basic statistics (distributions, confidence intervals, hypothesis testing).

Duties:

• Ingest, clean, and join large multi-plate experimental datasets (e.g., biochemical assays, plate maps, metadata) using Python (pandas, numpy).
• Implement repeatable analyses via notebooks and scripts.
• Select the right summary/metric for the biology and assay geometry and documents the rationale.
• Implement QA/QC checks (sanity checks, outlier flags).
• Produce decision-grade visualizations and concise exploratory data analysis (EDA) summaries.
• Package and share results with clear documentation.
• Collaborate extensively with experimental scientists - asking questions, reflecting on objectives, and agreeing on success criteria before executing.
• Translate technical results to the right abstraction level.
• Deliver analyses that directly inform next-step experiments, assay optimization, or go/no-go decisions.