Senior Developer

HEALTHSTREAM INC•Nashville, TN

7d•$98,000 - $120,000•Hybrid

About The Position

HealthStream's Platform Architecture team is seeking a Senior Developer to join our AI Technology team. This team builds AI-powered services and capabilities integrated across HealthStream's product portfolio, serving healthcare organizations nationwide. In this role, you will lead the design, development, and delivery of production-grade AI/ML services — including large language model (LLM) integration, vector search systems, prompt engineering pipelines, and AI service APIs — all within a HIPAA-compliant healthcare SaaS environment. As a Senior Developer, you will serve as a technical anchor for AI initiatives, collaborating closely with product managers, architects, and cross-functional engineering teams. You will mentor junior developers, contribute to architectural decisions, and set the bar for engineering quality on a team where AI innovation directly impacts to develop and empower people to deliver the highest quality of care.

Requirements

Bachelor's or Master's degree in Computer Science, Software Engineering, Data Science, AI/ML, or a closely related field.
5+ years of professional software development experience, with at least 2 years focused on AI/ML or LLM-based product development.
Demonstrated experience shipping production AI features — including LLM integrations, vector search, or ML inference APIs.
Hands-on experience with cloud-native development on AWS (Lambda, API Gateway, DynamoDB, S3, IAM); Azure OpenAI experience is a strong plus.
Experience working in regulated industries (healthcare, finance, legal) with an understanding of data privacy requirements (HIPAA awareness preferred).
Track record of leading technical initiatives end-to-end: from design through deployment and ongoing operations.
Expert-level proficiency in Python; strong working knowledge of JavaScript/TypeScript.
Deep familiarity with LLM application design: RAG pipelines, prompt chaining, function calling, embedding models, and vector similarity search.
Experience with AI/ML libraries and frameworks: PyTorch, TensorFlow, Hugging Face Transformers, LangChain, or LlamaIndex.
Strong command of RESTful API design and implementation; familiarity with GraphQL or gRPC is a plus.
Proficiency with infrastructure-as-code and CI/CD practices (Terraform, GitHub Actions, or equivalent).
Familiarity with vector databases (Pinecone, pgvector, FAISS, or similar).
Comfort with containerization (Docker) and serverless deployment patterns.
Exceptional problem-solving skills and intellectual curiosity about frontier AI/ML developments.
Strong written and verbal communication skills — able to explain complex technical concepts to non-technical stakeholders.
Proven ability to lead technical work independently while aligning with broader team and product goals.
Collaborative mindset with experience mentoring early-career engineers.
Self-directed, organized, and comfortable managing multiple workstreams in a fast-moving environment.

Responsibilities

Adhering to all HealthStream security policies, procedures, and assigned training.
Designing, developing, and owning production AI service APIs that power intelligent features across HealthStream's SaaS products.
Architecting scalable LLM integration pipelines including retrieval-augmented generation (RAG), vector embedding workflows, and multi-step prompt orchestration.
Building and maintaining AI microservices on AWS (Lambda, API Gateway, DynamoDB, S3) following security and compliance standards.
Leading technical design reviews and contributing to architectural decision records (ADRs) for AI platform components.
Developing, optimizing, and maintaining prompt pipelines for LLM-based product features (e.g., content summarization, semantic search, recommendations).
Evaluating and integrating Azure OpenAI services (GPT-4o-mini, text-embedding-ada-002) and other model providers into product workflows.
Establishing prompt versioning, A/B testing, and regression testing practices for LLM-powered features.
Defining and implementing AI evaluation frameworks — including benchmark datasets, quality metrics, and automated test harnesses for AI outputs.
Instrumenting AI services with observability tooling (logging, tracing, latency monitoring) suitable for regulated healthcare environments.
Owning incident response for AI service reliability, leading root cause analysis and remediation.
Mentoring and guiding junior developers and interns; conducting code reviews with constructive technical feedback.
Partnering with product managers and UX designers to translate AI capabilities into user-facing features.
Participating actively in Agile sprint ceremonies: planning, standups, demos, and retrospectives.
Presenting technical findings, architecture proposals, and project outcomes to engineering and product leadership.