Scientist, Bioinformatics

Mercy BioAnalytics; Waltham, Northern (MA, KY); Hybrid; USD 120,000 - 128,000; Full time

Job summary

Mercy BioAnalytics, Inc. is a biotechnology company focused on early cancer detection through biomarker discovery and data-driven approaches.

We are seeking a passionate Scientist to advance our Bioinformatics team, integrating public datasets with internal screening data to prioritize biomarkers and build scalable data infrastructure. The role emphasizes collaboration, cloud-based workflows, and AI-assisted pipelines to accelerate discovery for our life-saving programs.

Qualifications

• BSc/MS in bioinformatics, computational biology, or genomics with 5 years of industry experience, or a PhD.
• Working knowledge of cancer biology and biomarker development, including tumor heterogeneity.
• Expert-level Python and/or R, strong SQL, and Git.
• Cloud experience (AWS) and familiarity with workflow orchestration.
• Experience with single-cell RNA-seq analysis and co-expression questions preferred.
• Experience building analytical apps with Shiny or Streamlit.

Responsibilities

• Biomarker Discovery and Prioritization integrating public and internal datasets.
• Develop a biomarker prioritization framework considering tumor specificity and accessibility.
• Extend prioritization to marker combinations and single-cell analyses.
• Analyze internal data including QC, normalization, and hit calling.
• Collaborate with lab team on screening design and candidate evaluation.
• Design and build data warehouse and self-service dashboards.

Skills

Python

R

SQL

Git

Shiny/Streamlit

AI tooling

Cloud computing

Education

PhD

BSc/MS in bioinformatics / related field

Tools

AWS

Airflow

Docker

Kubernetes

Job description

Mercy BioAnalytics, Inc., is a biotechnology company dedicated to reducing suffering and saving lives through the early detection of cancer. Backed by extensive clinical validation, we are advancing one of the most important innovations in modern medicine: detecting cancer at its earliest, most treatable stages through a simple blood draw.

We are looking for a passionate and experienced Scientist to join our Bioinformatics team. The successful candidate will enable biomarker discovery for our early detection programs, integrating public cancer datasets and internal screening data to generate prioritized candidates, and will build the data infrastructure and tooling that supports similar biomarker discovery work for computational and laboratory colleagues.

Candidates for this position must enjoy working for a fast-paced, cutting-edge company, be able to work in a highly collaborative and teamwork-oriented environment and exhibit a passion for being a part of our life-saving mission.

Responsibilities:

Biomarker Discovery and Prioritization

• Integrate public cancer resources, including TCGA, GTEx, CPTAC and other proteomics datasets, single-cell atlases, CCLE/DepMap, and the Human Protein Atlas, into coherent and queryable evidence layers that support repeatable analysis
• Develop and maintain a biomarker prioritization framework that ranks candidates on tumor specificity, off-target expression, surface accessibility, vesicle association, and reagent availability
• Extend prioritization to marker combinations and pairs, reflecting how Mercy’s assays generate signal, including co-expression analysis at single-cell resolution
• Analyze internal data from cell line and clinical sample profiling, including QC, batch effect assessment, normalization, replicate and plate-level diagnostics, and hit calling
• Partner with the laboratory team on screening design, sample size, and reagent and binder selection, and evaluate candidate biomarkers for early detection

Data Platform Architecture and Engineering

• Design and build the data warehouse spanning sample and clinical metadata, screening results, public reference data, and analysis outputs
• Build self-service access for the laboratory team through dashboards, browsable candidate and screening views, and lightweight applications
• Establish pragmatic engineering practice for the group, including version control, containerized environments, workflow orchestration, and reproducible analysis, applying AI-based development tools to build and deploy quickly

Requirements:

• BSc/MS in bioinformatics, computational biology, genomics, biostatistics, or a related field plus 5 years’ industry experience, or a PhD; minimum 3+ years of industry experience in biotech, diagnostics, or pharma is required
• Working knowledge of cancer biology and biomarker development, including tumor heterogeneity, staging, and the distinction between prognostic and diagnostic markers
• Demonstrated experience integrating multiple public omics resources, such as TCGA, GTEx, CPTAC, and single-cell atlases, into a substantive analysis
• Expert-level proficiency in Python and/or R, strong SQL, and Git
• Cloud experience, preferably AWS, and familiarity with workflow orchestration tools
• Excellent verbal and written communication skills as well as interpersonal skills
• Single-cell RNA-seq analysis experience, particularly for co-expression or cell-type-specific marker questions, is preferred
• Experience building analytical applications for non-computational users, using tools such as Shiny or Streamlit, with evidence of sustained adoption, is preferred
• Hands-on use of modern AI development tooling, including coding agents and LLM-assisted pipelines, to accelerate delivery is preferred
• Ability to work in a fast-paced environment and adapt to changing priorities

Hiring Manager: Director, Software and AI

Location: Remote, with periodic travel to office in Waltham, MA

Status: Full Time

Job ID: DEV014

Base Salary Range: $120,000 – $128,000