Senior AI Platform Engineer — Production-Grade AI

MultiPlan; McLean (VA); On-site; USD 190,000 - 210,000; Full time

Job summary

Claritev is seeking a Principal AI Platform Engineer to lead design, development, deployment, and operation of AI foundation capabilities powering its healthcare products.

You will architect reusable AI capabilities (document ingestion, RAG, entity extraction, model/LLM services, agents) and deliver production-grade microservices, APIs, SDKs, and platform components. You will mentor engineers and shape the AI Foundry strategy.

Qualifications

• Bachelor's degree in CS/Engineering or related field is required.
• 10+ years in software/platform engineering or related field.
• 5+ years shipping production AI/ML platform systems.
• 3+ years building AI/LLM/agentic systems.

Responsibilities

• Own engineering, deployment, operation, and improvement of production AI platform services.
• Partner with stakeholders to define platform requirements and success metrics.
• Drive end-to-end production readiness across cloud deployment, scalability, resilience, and monitoring.
• Establish reusable platform frameworks, APIs, data contracts, and engineering patterns.
• Implement CI/CD, automated testing, versioning, controlled deployment, and SLO/SLI governance.
• Build observability and monitoring for AI quality, latency, and cost.
• Embed security and PHI/PII protection, lineage, and governance.
• Develop RAG and knowledge-retrieval capabilities and agent orchestration.

Skills

Python

Platform engineering

LLMOps

CI/CD

Observability

Security & governance

Problem solving

Communication

Cross-functional leadership

Cloud architecture

Education

Bachelor's degree in CS/Engineering/Data Science

Master's degree preferred

Tools

AWS

Azure

OCI

Kubernetes

APIs & SDKs

Embeddings/Vector search

Job description

Claritev is seeking a Principal AI Platform Engineer to lead design, development, deployment, and operation of AI foundation capabilities powering its healthcare products.

You will architect reusable AI capabilities (document ingestion, RAG, entity extraction, model/LLM services, agents) and deliver production-grade microservices, APIs, SDKs, and platform components. You will mentor engineers and shape the AI Foundry strategy.