AI Integration Developer

AI Integration Developer

An opportunity is available for an AI Integration Developer to design, enhance, and maintain AI-assisted workflows supporting scientific data. This role involves collaborating with scientific domain experts to understand data structures, implement dataset taxonomies, and orchestrate the migration of datasets for computational analysis using approved LLMs. The position focuses on automation, orchestration, and data structuring to build impactful solutions for research scientists.

Key Responsibilities

• Collaborate with scientific domain experts to understand datasets, locations, and desired outcomes.
• Design and implement AI-driven data workflows, including data preparation, metadata structuring, and LLM-enabled orchestration.
• Filter, sanitize, normalize, and prepare data for long-term storage and sharing.
• Package data with AI-enabling metadata into HDF5 format.
• Create mechanisms to migrate and inventory data for easy retrieval.
• Build accessible and user-friendly interfaces and workflows for research staff.
• Develop solutions using revision control and adhere to cybersecurity and IT standards.
• Deliver a minimum viable product (MVP) within the first 90 days, followed by further refinement and feature additions.

Required Qualifications

Education: An Associate or bachelor's degree in computer science, information technology, system administration, or a closely related field, or equivalent experience is required.

Experience: A minimum of two years of experience in software development and/or system administration is required.

Technical Skills

• Strong understanding of AI, LLMs, and prompt engineering.
• Proficiency in Python scripting for automation and workflow development.
• Experience building data pipelines or ETL-like processes, including data cleansing, normalization, and transformation.
• Working knowledge of REST APIs.
• Familiarity with Git or other revision control systems.
• Experience with CI/CD pipelines (e.g., GitLab/GitHub).
• Strong skills in Linux (RHEL/Debian) command-line administration.
• Familiarity with relational databases such as MySQL or Oracle.

Preferred Qualifications

• Experience with AI workflow orchestration tools like Dify.
• Familiarity with GUI development using Python or web-based applications.
• Understanding of data workflows within scientific or research environments.
• Exposure to LLM-based data processing or automation use cases.

Work Environment

This is a full-time, 40-hour per week contract position. The work schedule is primarily remote, with a requirement to be on-site between 20-40% of the time. The role involves working with government-furnished equipment and adhering to all computer protection program policies and security requirements.

Compensation

The pay rate for this position ranges from $50.00 to $80.00 per hour. Compensation may vary based on factors including but not limited to experience, qualifications, and geographic location.