Bioinformatics Engineer

This is a fully remote position, open to applicants in United States.

📋 Description

• Design and develop synthetic data generation pipelines that mirror the structure and statistical characteristics of controlled-access datasets.

• Create realistic synthetic test and development datasets, including genomic sequence-style data modeled after dbGaP.

• Implement and fine-tune privacy-preserving techniques, such as differential privacy noise injection.

• Validate the fidelity of synthetic data through statistical distribution alignment, utility-preservation assessments, and performance comparison of downstream models against real-data benchmarks.

• Evaluate and document residual privacy threats, including re-identification, linkage, and membership inference risks.

• Collaborate with the Red-Team/Adversarial Security Lead and Biomedical Privacy & Gateway Engineer to deliver adversarial and edge-case synthetic scenarios.

• Contribute to methodology documentation and data provenance records for review by the institutional Data Access Committee.

• Work in partnership with cross-functional teams across federal agencies and their supporting partners.

• Engage with the Principal Investigator/Technical Lead and the larger Mind Moves project team.

⛳️ Requirements

• Proven experience in developing synthetic data generation pipelines utilizing statistical modeling, generative models (e.g., GANs, VAEs, diffusion), or agent-based simulations.

• Expertise in engineering and transforming large-scale genomic formats, including multi-sample VCFs, PLINK binary sets, or Hail MatrixTables.

• Experience handling complex, longitudinal clinical and phenotypic datasets.

• Advanced proficiency in Python and SQL.

• Practical experience with synthetic data, privacy, and scientific libraries such as Opacus, Diffprivlib, PyTorch, Hail, Polars, or Spark.

• Skills in data engineering and ETL processes, including pipeline design, schema modeling, and API integration.

• Familiarity with AI/data governance frameworks like NIST AI RMF and federal NIH/HHS compliance standards is preferred.

• A background in biomedical, bioinformatics, or life sciences is preferred.

• Experience in advancing synthetic data pipelines from proof of concept to production-grade, reusable tools.

• Excellent communication skills with the ability to document methodologies and risk assessments for non-technical and institutional stakeholders.

• U.S. work authorization for 1099 contracting; sponsorship is not available.

• Must be eligible to obtain and maintain a federal public trust credential/government badge.

• Professional working proficiency in English, encompassing reading, writing, speaking, and listening.

• Must reside in the Eastern Standard Time (EST) zone or within the United States.

🏝️ Benefits

• Hands-on experience with privacy-preserving data generation for cutting-edge AI/ML pipelines.

• Opportunity to work at the confluence of data engineering, privacy, and federal data governance.

• Mission-driven opportunities that have a measurable impact on secure AI systems managing sensitive genomic and health data.

• Remote work arrangement.

• Flexible contract schedule ranging from 20 to 25 hours per week.

• Chance to collaborate with federal agencies, NIH stakeholders, Data Access Committees, and supporting partners.