The ML Ops Engineer role is based in Reading, PA, requiring on-site work 5 days/week, with a max bill rate of $100/hour.
Responsibilities include designing multi-agent architectures with defined roles, toolboxes, memory, and safety policies; building high-quality Retrieval-Augmented Generation (RAG) pipelines with proper evaluation and guardrails; deploying solutions on AWS using Bedrock, Lambda, API Gateway, S3, DynamoDB, and OpenSearch; automating CI/CD, containerization, infrastructure-as-code, and data pipelines; instrumenting observability through telemetry, dashboards, and evaluations; ensuring reliable operation at scale with caching, rate limiting, and drift detection; and collaborating with cross-functional teams, documenting designs, and communicating insights.
Qualifications include a Bachelor's degree or equivalent experience, proven experience with agentic systems and RAG pipelines, strong cloud knowledge (preferably AWS Bedrock), CI/CD and containerization skills, and a passion for Generative AI. Preferred skills include experience with AWS services, Dataiku, agent frameworks, and relevant certifications.