AI Software Engineer
UT Southwestern Medical · Texas-Dallas-5323 Harry Hines Blvd
About this role
## AI Software Engineer ### Why UT Southwestern? With over 75 years of excellence in Dallas-Fort Worth, Texas, UT Southwestern is committed to excellence, innovation, teamwork, and compassion. As a world-renowned medical and research center, they invest in employees with opportunities for career growth, a highly competitive benefits package (healthcare, PTO and paid holidays, on-site childcare, wage/merit increases, and more), and a culture of teamwork and professionalism. ### Job Summary Works under minimal supervision to design, build, and ship **production AI features** within **DIMS (Discovery Information Management System)**—the Innovation Hub’s proprietary platform for managing faculty research Discovery Tracks. This is a hands-on software engineering role focused on delivering **working, maintainable code** (not research benchmarking or proof-of-concept experimentation). You will develop **agentic workflows**, **natural language search**, **retrieval pipelines**, and **model integrations** grounded in institutional scientific data. You’ll partner with the product owner, software developers, designers, and external technical collaborators to translate commercialization workflows into **accurate, traceable, and auditable** AI capabilities, and serve as the Innovation Hub’s primary technical owner for applied AI as DIMS scales. ### Essential Functions **Job Duties** - Build and ship production AI features in DIMS, including: - Multi-step agentic workflows - Natural language search - Structured extraction - Recommendation and matching capabilities - Design, build, and maintain AI agents end-to-end: - Prompt design and iteration - Tool/function definitions - Orchestration and routing across multi-step tasks - Context and memory management - Structured output contracts - Create reusable prompt/tool/orchestration patterns so new agents can be added without rebuilding shared infrastructure. - Establish prompt versioning, evaluation harnesses, regression tests, and acceptance criteria to ensure agent behavior is measurable, reproducible, and safe to release. - Integrate commercial and open LLMs via APIs (e.g., **Microsoft Azure Foundry/OpenAI Service** and other approved platforms), managing: - Model selection and versioning - Cost, latency, rate limiting - Failure handling - Develop retrieval and data pipelines that ground AI features in institutional and external sources (faculty/lab datasets, invention disclosure content, public scientific/IP sources), ensuring outputs remain **traceable to verifiable sources**. - Translate commercialization workflows and stage gate criteria into working features; participate in requirements definition, technical scoping, and release planning. - Implement guardrails, monitoring, and observability for: - Accuracy - Hallucinations - Data leakage - Cost - Ensure alignment with UTSW information security, data stewardship, compliance, and IP protections (pre-publication/pre-patent content). - Contribute to code review, technical documentation, version control, and deployment automation; support productionization and handoff of prototypes into supported platform capabilities. ### Qualifications **Education and Experience Required** - Bachelor’s degree in Computer Science, Engineering, or related field (or equivalent experience) - **4+ years** professional software engineering experience - Strong proficiency in **Python**; working knowledge of **TypeScript or JavaScript
Listing freshness
CronJobs last confirmed this listing 5h ago. If its source stops confirming the opening for seven days, this page is removed from active inventory.