Bachelor's degree in Computer Science, Data Science, Machine Learning, Biomedical Informatics, or related field; Master's preferred.
3-5 years of software engineering, data engineering, or MLOps experience; 1+ years in Generative AI or RAG applications.
Strong proficiency in Python, REST APIs, and Docker; experience with GCP Vertex AI or similar cloud stacks.
Experience with RAG pipelines, vector indexing, and agent orchestration frameworks.
Familiarity with healthcare IT standards (FHIR, HL7) and data privacy regulations.
Responsibilities
Write production-grade Python code for Retrieval-Augmented Generation (RAG) assistants.
Build multi-step agentic workflows using Google Agent Development Kit (ADK).
Contribute to flagship builds and support business unit teams with reusable components.
Configure safety controls and compliance measures for AI applications.
Integrate AI tools into CI/CD pipelines and ensure production readiness.
Instrument applications for observability and monitor performance metrics.
Benefits
Paid time off for vacations, holidays, and illness.
Comprehensive health insurance (medical, dental, vision, prescription).
401(k) retirement savings plan.
Education support and student loan assistance.
Life and disability insurance.
Flexible spending account.
Full Job Description
Job Description
Our Benefits:
Our team members enjoy a robust benefits package including:
Competitive compensation
Paid time off for vacations, holidays, and illness
Comprehensive health insurance (medical, dental, vision, prescription)
401(k) retirement savings plan
Education support and student loan assistance
Life and disability insurance
Flexible spending account
Job Summary
The AI Engineer is a hands-on software and AI builder within the CHS Enterprise AI Center of Excellence (CoE), operating under a collaborative hub-and-spoke model. Working directly from CoE reference architectures and pre-secured "golden-path" templates, you will write production code to build, test, and deploy Generative AI assistants, agentic workflows, and AI-for-BI data agents. You will connect foundation models to enterprise data interfaces, configure automated safety and privacy guardrails on Google Cloud (Vertex AI), and instrument day-to-day observability and cost tracking to deliver reliable healthcare solutions.
Key Responsibilities
GenAI & RAG Application Development: Writes clean, production-grade Python code to build and optimize Retrieval-Augmented Generation (RAG) assistants using CoE golden-path templates. Implements document ingestion pipelines (chunking, embedding, and access tagging) and configures retrieval indexes that enforce user entitlements and return grounded, cited responses.
Agentic Workflow & MCP Tool Engineering: Builds multi-step agentic workflows using the Google Agent Development Kit (ADK) and Agent Runtime, configuring session state, bounded memory, and step/spend limits. Develops and registers scoped Model Context Protocol (MCP) tool servers on Cloud Run to safely connect agents with approved enterprise APIs and data platform interfaces.
AI-for-BI & Spoke Solution Delivery: Contributes hands-on engineering to CoE-led flagship builds (such as Looker Data Agents) and supports business unit spoke teams in implementing reusable platform components.
Guardrails & Security Configuration: Configures standard ingress and egress safety controls using Model Armor (for prompt injection and sensitive-data scanning), tool allow-lists, and least-privilege IAM/agent identities to ensure compliance with HIPAA, CMS, and AI Governance Committee (AIGC) standards.
CI/CD, Testing & Release Readiness: Wires AI applications and tools into standardized CoE CI/CD pipelines across strict dev, QA, and production environments. Writes automated unit tests, groundedness checks, and agent scenario evaluations to satisfy production-readiness gate criteria.
Observability & Trajectory Debugging: Instruments applications with OpenTelemetry traces, metrics, and compliance audit logs (capturing prompts, tool calls, and data access) in Google Cloud Observability. Monitors token consumption, latency, and run failures through the Enterprise AI Gateway to debug agent trajectories and optimize performance.
Minimum Qualifications
Education: Bachelor's degree in Computer Science, Data Science, Machine Learning, Biomedical Informatics, or a related quantitative engineering field required; Master's degree preferred.
Experience: 3-5 years of professional software engineering, data engineering, or MLOps experience, including at least 1+ years of dedicated, hands-on experience building and shipping Generative AI, RAG, or LLM-backed applications into production environments.
Knowledge, Skills and Abilities
Strong hands-on proficiency in Python, REST APIs, and containerization (Docker), with practical experience building on GCP Vertex AI (including Model Garden, Agent Development Kit [ADK], Cloud Run, and Model Armor) or comparable cloud AI stacks (Azure/OpenAI).
Experience implementing RAG pipelines, vector/search indexing, and tool-calling/agentic orchestration frameworks, alongside familiarity with Model Context Protocol (MCP) or enterprise API integrations.
Practical experience working within automated CI/CD pipelines, Git workflows, dev/QA/prod environment boundaries, and observability/tracing tools (such as OpenTelemetry, Cloud Monitoring, or LangSmith/Langfuse) to debug latency, token usage, and failure modes.
Working knowledge of healthcare IT standards (FHIR, HL7) and data privacy fundamentals, with the ability to implement PII/PHI redaction and audit logging aligned with HIPAA and CMS requirements.
Ability to translate functional requirements into modular, well-tested code, following established architectural blueprints and production checklists to deliver reliable solutions.
This is a fully remote opportunity
This position is not eligible for immigration sponsorship now or in the future. Applicants must be authorized to work in the U.S. for any employer.