Note: The job is a remote job and is open to candidates in USA. WelbeHealth serves vulnerable seniors through the PACE program and is seeking an AI Engineer I to support the development of AI-powered healthcare and operational solutions. The role assists with enterprise large language model applications, retrieval-augmented generation systems, agentic workflows, cloud deployments, prototyping, testing, and responsible AI practices under the guidance of senior engineers.
Responsibilities
- Assist in building and testing AI-powered applications using enterprise LLMs (OpenAI, Anthropic Claude, Google Gemini) under the guidance of senior engineers. Help translate PACE program business requirements into early-stage AI prototypes and proofs of concept. Support prompt engineering, structured output handling, and basic function/tool calling integrations
- Contribute to the development and testing of retrieval-augmented generation (RAG) systems that ground AI responses in WelbeHealth’s proprietary data. Assist with vector database setup, embedding strategies, and chunking optimization under senior direction. Help evaluate retrieval quality and document findings
- Participate in rapid POC development cycles, contributing code, documentation, and iterative improvements. Assist in validation and QA testing of new AI use cases. Actively seek feedback, ask questions, and apply learnings to improve output quality
- Support cloud-based deployments in Azure environments with guidance on Docker, private endpoints, and secure configurations. Learn and follow best practices for AI/ML operations, including monitoring, versioning, and CI/CD pipelines. Assist in maintaining documentation for AI services and infrastructure
- Stay curious about emerging AI tools, model releases, and techniques. Share relevant findings with the team and help evaluate new approaches that could benefit participants and operations. Participate in team demos, retrospectives, and knowledge-sharing sessions
Skills
- Bachelor's Degree in Computer Science, Data Science, Software Engineering, or a related field required; relevant coursework or bootcamp training is a plus
- Coursework or self-directed study in machine learning, natural language processing, or AI application development is a plus
- Relevant certifications (e.g., Azure AI Fundamentals, AWS Cloud Practitioner, Google ML) are a plus; Working proficiency in Python, including the ability to write and debug scripts, interact with APIs, and work with common data structures
- Foundational understanding of artificial intelligence and machine learning concepts, including embeddings, vector search, prompt engineering, and retrieval techniques
- Exposure to large language model (LLM) platforms and APIs such as OpenAI, Anthropic, or Google Gemini through academic projects, internships, personal projects, or professional experience
- Exposure to cloud platforms such as Microsoft Azure, Amazon Web Services (AWS), or Google Cloud Platform (GCP) preferred; Familiarity with retrieval-augmented generation (RAG) concepts and vector database such as Pinecone, Weaviate, Chroma, or similar tools preferred
- Exposure to AI orchestration or agentic frameworks such as LangChain, LangGraph, or similar technologies preferred; Experience using version control tools such as Git and familiarity with basic CI/CD concepts and development workflows preferred; Basic understanding of healthcare data privacy and security requirements, including HIPAA and protected health information (PHI) handling practices preferred
Benefits
- Medical insurance coverage (Medical, Dental, Vision)
- 17 days of personal time off (PTO)
- 12 holidays observed annually
- 6 sick days
- 401K savings + match
- Bonus as part of the comprehensive compensation package
Company Overview
Company H1B Sponsorship