Bioinformatics Data Scientist

Spectrix Analytical Services, LLC; Cambridge (MA); On-site; USD 150,000 - 210,000; Full time

Benefits offered by this job

401(k)

401(k) matching

Dental insurance

Employee assistance program

Flexible schedule

Flexible spending account

Health insurance

Health savings account

Life insurance

Paid time off

Parental leave

Professional development assistance

Referral program

Retirement plan

Tuition reimbursement

Vision insurance

Job summary

Spectrix Analytical Services, LLC is seeking a highly qualified scientist to advance computational proteomics and translational research through scalable, cloud‑ready analytics. You will integrate proteomics with other omics, build robust workflows and dashboards, and leverage ML and AI to drive biological insights for drug discovery programs.

The role emphasizes collaboration with computational scientists and discovery biology teams, with a focus on reproducible software engineering practices

Qualifications

• Doctorate in bioinformatics, computational biology, data science, statistics, CS, systems biology, biochemistry, chemistry, or related quantitative field.
• Hands‑on experience with high‑dimensional biological or biomedical data such as proteomics, LC‑MS, transcriptomics, single‑cell data, spatial omics, or other omics modalities.
• Strong proficiency in R and/or Python for data analysis, statistical modeling, visualization, and reproducible scientific computing.
• Solid understanding of experimental design, data QC, normalization, missing-value assessment and imputation, feature selection, and advanced statistical modeling.
• Experience with scalable computing and cloud environments, including AWS and workflow systems for large datasets.
• Experience deploying workflows or data products on AWS, Nextflow, Snakemake, Airflow, Docker, ECS, or similar systems.
• Experience delivering software/data products with Posit/RStudio, Shiny, Dash, Streamlit, FastAPI, Flask, or similar platforms.

Responsibilities

• Examine large-scale proteomics and multi‑omics data to support biomarker discovery and pharmacodynamic analysis.
• Design scalable, reproducible analytical workflows, data pipelines, dashboards, and data products for scientific users.
• Apply ML/AI approaches to enhance interpretation, workflow automation, and knowledge extraction.
• Merge proteomics data with transcriptomics, genomics, genetics, and other modalities.
• Collaborate with computational scientists, biologists, and data teams to define strategies and communicate results clearly.
• Promote data QC, reproducible analysis, and responsible use of AI‑assisted tools.

Skills

Biostatistics

R

Python

Machine learning

Data visualization

Communication

Independent work

Team collaboration

Education

Doctorate in bioinformatics or related quantitative field

Tools

DIA-NN

Spectronaut

MaxQuant

FragPipe

Proteome Discoverer

Skyline

Shiny

Dash

Streamlit

Job description

Contribute to drug discovery and translational research by enabling computational proteomics, multi-omics analytics, scalable data workflows, and AI driven scientific analyses.

Responsibilities

• Examine large scale proteomics and multi-omics data to support biomarker discovery, pharmacodynamic analysis, pathway and causal inference, disease biology, and drug discovery programs.
• Design scalable, reproducible, cloud‑ready analytical workflows, data pipelines, reports, dashboards, APIs, and data products for scientific users.
• Utilize statistical modeling, machine learning, and AI/LLM powered approaches to enhance biological interpretation, knowledge extraction, workflow automation, and scientific decision support.
• Merge proteomics data with orthogonal modalities such as transcriptomics, genomics, genetics, perturbation data, metadata, and translational annotations.
• Partner with computational scientists, mass spectrometry specialists, discovery biologists, translational researchers, and data science teams to define analytical strategies and clearly communicate results.
• Champion data QC, reproducible analysis, workflow development, software engineering standards, and responsible use of AI‑assisted scientific tools.

Requirements

• Doctorate in bioinformatics, computational biology, data science, statistics, computer science, systems biology, biology, biochemistry, chemistry, engineering, or a related quantitative field.
• Hands‑on experience with high‑dimensional biological or biomedical data such as proteomics, LC‑MS, Olink, SomaScan, transcriptomics, single‑cell data, spatial omics, genomics, genetics, or other omics modalities.
• Strong proficiency in R and/or Python for data analysis, statistical modeling, visualization, and reproducible scientific computing.
• Solid understanding of experimental design, data QC, normalization, missing-value assessment and imputation, feature selection, and advanced statistical modeling for high‑dimensional data, including linear and mixed‑effects models, Bayesian methods, biological signal deconvolution, pathway interpretation, and communicating findings.
• Experience with scalable computing and cloud environments, including AWS services and workflow‑based analysis systems for large scientific datasets.
• Proficiency with machine learning, AI, and LLM powered analytics, including developing robust agentic or multi‑agent frameworks for scientific workflows.
• Familiarity with drug discovery, translational research, biomarker discovery, perturbation biology, pharmacodynamic studies, disease biology, or related biomedical contexts.
• Ability to work independently on complex analytical problems and convey results clearly to scientific stakeholders.

Technologies

• R
• Python
• AWS
• Nextflow
• Snakemake
• Airflow
• Docker
• AWS Batch
• ECS
• DIA-NN
• Spectronaut
• MaxQuant
• FragPipe
• Proteome Discoverer
• Skyline
• Shiny
• Dash
• Streamlit
• FastAPI
• Flask
• Posit/RStudio
• Posit Connect
• Claude
• Parquet
• SQL
• Git
• Olink
• SomaScan

Benefits

• 401(k)
• 401(k) matching
• Dental insurance
• Employee assistance program
• Flexible schedule
• Flexible spending account
• Health insurance
• Health savings account
• Life insurance
• Paid time off
• Parental leave
• Professional development assistance
• Referral program
• Retirement plan
• Tution reimbursement
• Vision insurance

Preferred Qualifications

• Postdoctoral, industry, or equivalent applied research experience after PhD.
• Direct experience with computational proteomics across platforms such as LC‑MS proteomics, phosphoproteomics, DIA/SWATH, DDA, TMT, label‑free quantification, PTM analysis, spectral library generation and prediction, and affinity‑based proteomics such as Olink or SomaScan.
• Hands‑on experience with proteomics software, outputs, or data structures from tools like DIA‑NN, Spectronaut, MaxQuant, FragPipe, Proteome Discoverer, Skyline, or similar platforms.
• Experience building reusable scientific workflows, analytical pipelines, applications, dashboards, APIs, reports, or self‑service data products for scientists.
• Experience deploying analytical workflows or data products on AWS or comparable clouds using Nextflow, Snakemake, Airflow, Docker, AWS Batch, ECS, or equivalent systems.
• Experience delivering R and Python software and data products with Posit/RStudio, Posit Connect, Shiny, Dash, Streamlit, FastAPI, Flask, or similar platforms.
• Strong software engineering practices including Git, modular code, documentation, testing, and reproducible workflow development.
• Hands‑on experience building LLM enabled applications or workflows using Claude or other large language models, including RAG systems, tool‑using agents, prompt engineering, evaluation frameworks, LLMOps, or scientific knowledge extraction.
• Experience applying ML or foundation-model approaches to biological data, including representation learning, multimodal modeling, classification/regression, embedding‑based retrieval, generative AI, or related methods.
• Experience with data modeling, SQL, Parquet, metadata management, data lake architectures, or large scale biological data warehouses.
• Strong publication record, open source contributions, or demonstrated delivery of reusable computational tools, analytical platforms, scientific workflows, or production quality internal data products.

Strong Differentiators

• Ability to bridge computational proteomics, biological interpretation, cloud engineering, bioinformatics methodology development, and AI/ML/LLM workflow implementation for life science applications.
• Proven success building tools, analytical methods, or platforms adopted by experimental, translational, or computational scientists.
• Contributions to peer reviewed publications in bioinformatics, computational biology, proteomics, machine learning, systems biology, or related fields.
• Experience designing AI assisted, machine learning, or agentic workflows that are reproducible, traceable, scientifically reliable, and suitable for biological and biomedical research.
• Strong understanding of connecting omics data, pathway biology, perturbation data, genetics, and drug discovery questions into reusable analytical systems.
• Ability to develop and publish novel analytical methodologies when appropriate.
• Track record applying AI and ML techniques to life science datasets, including biomarker discovery, target identification, predictive modeling, knowledge extraction, or multi‑omics integration.
• Ability to help shape future scientific AI strategy beyond executing predefined analyses.

Experience

• Bioinformatics: 1 year (Preferred)