Remote AI Engineer: RAG Pipelines & LLMs (Healthcare)

Eliassen Group

Columbus (OH)

Remote

USD 125,000 - 165,000

Full time

5 days ago

Be an early applicant

Application generator

A complete application in a minute — tailored resume and cover letter, ready to send.

Get past ATS filters

Job summary

Eliassen Group is seeking an AI Engineer to design, test, and deploy AI-powered solutions for healthcare within the PACE program. The role focuses on enterprise AI models to deliver context engines, RAG pipelines, and agentic workflows. You will translate emerging AI capabilities into production-ready solutions and collaborate with stakeholders in a remote setting.

The position is full-time with a competitive salary and comprehensive benefits. Applicants must work on a W2 basis.

Qualifications

Minimum three years of hands-on experience in AI/ML engineering, applied AI development, or software engineering with an AI focus.
Experience designing and deploying RAG pipelines including vector databases and retrieval optimization.
Experience building on commercial LLM APIs with prompt engineering, structured outputs, tool calling, and context management.
Advanced proficiency in Python for AI applications, APIs, and data pipelines.
Hands‑on experience with Azure AI services and Docker in secure cloud environments.
Proficiency with DevOps and CI/CD using Azure DevOps or equivalent.
Understanding of agentic architectures and frameworks such as LangChain, LangGraph, Semantic Kernel, or Copilot Studio.
Experience in Agile or Scrum with iterative development and rapid POCs.
Familiarity with HIPAA, PHI handling, and healthcare compliance preferred.
PACE program knowledge preferred.
Experience benchmarking LLM providers across accuracy, cost, latency, and safety preferred.
Secondary experience with AWS AI/ML services is a plus.
Strong organizational and communication skills with ability to work independently and prioritize.
Experience working with people from diverse backgrounds and a commitment to serving vulnerable seniors.

Responsibilities

Design, build, and deploy AI-powered applications using enterprise LLMs to meet PACE business requirements.
Architect and implement RAG systems grounded in proprietary data with accuracy, relevance, and compliance.
Own the development lifecycle from ideation and POC through validation, iteration, and production deployment.
Research and build agentic AI workflows using frameworks such as LangGraph, LangChain, or Copilot Studio.
Architect and deploy AI services in private cloud environments, primarily Azure, using secure configurations.
Evaluate and integrate across multiple models based on performance, cost, latency, and compliance.
Implement AIOps and MLOps practices including monitoring, versioning, automated testing, and CI/CD.
Continuously evaluate emerging AI tools and models and recommend improvements.
Work a varied schedule that may include evenings, nights, weekends, and overtime.
Complete required documentation accurately and on time while protecting privacy and confidentiality.
Follow policies and procedures, participate in quality improvement, training, and meetings.
Communicate regularly with the supervisor and team on workload and priorities.
Complete mandated trainings and occupational health screenings on time.
Exercise flexibility as business needs evolve and perform other duties as assigned.