Senior Systems Engineer – Clinical NLP Research Support

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

📋 Description

• Develop methods and infrastructure, and enhance NLP and LLM strategies to identify predictor variables for suicidal thoughts and behaviors within VA EHR clinical notes.

• Construct and sustain custom tokenization and text-processing pipelines that operate at a population scale across the Million Veteran Program cohort.

• Extract and validate phenotypes such as suicidal ideation, suicide attempts, and related exposures for gene-by-environment analyses.

• Prepare, document, and transfer datasets that are ready for analysis to the statistical genetics team of the study.

• Oversee code version control, testing, documentation, and reproducibility within the VA research computing environment.

• Ensure adherence to VA privacy and information security standards regarding PHI and PII.

• Diagnose pipeline performance, scalability, and data quality issues, implementing necessary improvements.

• Collaborate with the Principal Investigator and the study team, providing updates on project milestones.

• Create technical documentation, workflow documentation, and materials for handoff.

⛳️ Requirements

• Bachelor's degree in computer science, engineering, data science, informatics, or a related technical discipline.

• Over 8 years of experience in computer systems engineering, software development, data engineering, or technical implementation.

• Proficient in AI/SI methods development, including the creation of LLM models for EHR text evaluation within a federal research context.

• Familiarity with the technical lifecycle of this research type, including custom tokenization and population-scale projects.

• Experience in programming and developing data pipelines.

• Knowledge of working with PHI and PII in compliance with VA privacy and security regulations.

• Capability to work independently in a part-time, remote capacity while adhering to project deadlines.

• Effective communication skills with both technical and research stakeholders.

• Ability to obtain and maintain a public trust clearance.

• Legal authorization to work in the United States.

• Extensive experience in developing NLP or LLM methods for VA.

• Background in supporting research studies, especially in genomics, with familiarity in programs like the Million Veteran Program.

• Experience with transformer-based models, model fine-tuning, or custom tokenizer development.

• Proven experience in developing or validating computable phenotypes, including chart review or annotation workflows.

• Familiarity with GPU-based or high-performance computing environments.

• Understanding of mental health or suicide prevention research.

• Experience in version control, technical documentation, and reproducible workflows.

• High level of professionalism, discretion, and sound judgment when handling sensitive information.

• Ability to fulfill the stated physical requirements, which include extended periods of sitting, computer use, verbal and written communication, and occasional standing, walking, bending, or lifting up to 15 pounds.

🏝️ Benefits

• Part-time schedule of 20 hours per week.

• Fully remote position.

• Potential for contract extension into the next option year based on contract continuation and program requirements.

• Opportunity to contribute to a Department of Veterans Affairs research study focused on suicide prevention.

• Potential to engage with population-scale Million Veteran Program data and clinical NLP/LLM methodologies.