Job Title: AI Engineer
Location: Remote
Duration: 6-8 Months
Job Summary:
The AI Engineer is responsible for building, testing, and deploying AI-powered solutions that address real-world healthcare challenges within our PACE (Program of All-Inclusive Care for the Elderly) program. The AI Engineer will leverage enterprise AI models to not build or fine-tune them to create intelligent applications such as participant context engines, retrieval-augmented generation (RAG) pipelines, and agentic workflows. The AI Engineer will stay current with the rapidly evolving AI landscape and translate emerging capabilities into production-ready solutions for our business. The AI Engineer collaborates effectively with colleagues and stakeholders to promote WelbeHealth values, team culture, and mission.
Job Responsibilities:
- Enterprise AI Application Development: Design, build, and deploy AI-powered applications using enterprise LLMs (OpenAI, Anthropic Claude, Google Gemini).
- Translate PACE business requirements such as building rich participant context into production-ready AI solutions.
- RAG Pipeline Engineering: Architect and implement retrieval-augmented generation (RAG) systems that ground AI responses in WelbeHealth's proprietary data, ensuring accuracy, relevance, and compliance with healthcare data standards.
- Hands-On Prototyping & Delivery: Own the full development lifecycle for new AI use cases from ideation and rapid POC development through validation, iteration, and production deployment.
- Agentic Framework Development: Research and build agentic AI workflows (using frameworks such as LangGraph, LangChain, or Copilot Studio) that evolve our systems toward autonomous, goal-oriented agents capable of handling complex multi-step healthcare processes.
- Secure Cloud Deployment: Architect and deploy AI services within private cloud environments (primarily
- Azure; AWS as needed), utilizing Docker containers, private endpoints, managed identities, and secure VNET configurations.
- Multi-Model Orchestration: Evaluate and integrate across the frontier model landscape, selecting the right model for each use case based on performance, cost, latency, and compliance requirements.
- Operational Excellence: Implement AIOps and MLOps best practices monitoring, versioning, automated testing, and CI/CD pipelines to ensure all AI applications are reliable, scalable, and maintainable.
- Technology Scouting: Continuously evaluate emerging AI tools, techniques, and model releases.
- Proactively recommend new approaches that can improve participant outcomes, operational efficiency, or developer productivity.
- Must be willing and have the ability to work a varied schedule that may include evening nights, weekends, and overtime.
- Complete all required documentation in a timely and accurate manner.
- Protect privacy and maintain confidentiality of all company procedures and information about team members, participants, and families.
- Follow WelbeHealth policies and procedures and participate in any required Quality Improvement activities, staff training, and meetings.
- Communicate regularly with the supervisor and team regarding workload and priorities.
- Timely completion of all mandated trainings and education.
- Timely completion of all mandated occupational health screenings as needed.
- Exercises flexibility in performing assignments as business needs evolve.
- Other duties as assigned.
Skills:
Required Skills & Experience:
- Minimum of three (3) years of hands-on experience in AI/ML engineering, applied AI development, or software engineering with a strong AI focus.
- Experience and competency working with people from diverse backgrounds and cultures.
- RAG & Retrieval Systems: Demonstrated experience designing and deploying retrieval augmented generation pipelines, including vector databases, embedding strategies, chunking optimization, and retrieval evaluation.
- Enterprise LLM Integration: Proven ability to build applications on top of commercial LLM APIs (OpenAI,
- Anthropic, Google) including prompt engineering, structured output handling, function/tool calling, and context window management.
- Python: Advanced proficiency in Python for AI application development, API integration, and data pipeline construction.
- Cloud & Containerization: Hands-on experience with Azure AI services (AI Foundry, Managed Identities, Key Vault, private networking) and Docker-based deployments in secure cloud environments.
- DevOps & CI/CD: Proficiency with Azure DevOps (or equivalent) for building CI/CD pipelines that automate testing and deployment of AI applications.
- Agentic AI Patterns: Solid understanding of agentic architectures and frameworks such as LangChain, LangGraph, Semantic Kernel, or Copilot Studio.
- Agile Delivery: Experience working in Agile/Scrum environments with iterative development cycles and rapid POC delivery.
- Excellent organizational and communication skills.
- Ability to work independently with minimal supervision.
- Demonstrated ability to prioritize in a fast-paced environment.
- Commitment to unlocking the full potential of our most vulnerable seniors.
Preferred Skills & Experience:
- Healthcare Domain: Familiarity with HIPAA, PHI handling, and the compliance requirements unique to healthcare technology.
- PACE Program Knowledge: Understanding of the PACE model of care and how technology can improve participant outcomes and operational workflows.
- Model Evaluation: Experience benchmarking and comparing LLM providers across dimensions such as accuracy, cost, latency, and safety.
- AWS: Secondary cloud experience with AWS AI/ML services.
Education:
Required Education:
Bachelor’s Degree required in Computer Science, AI, or Computer Engineering.
Preferred Education:
Master’s Degree in the above.
