AI/ML Engineer — Agentic AI Builder

MatchPoint Solutions is a fast-growing IT-Engineering services company providing technology solutions to clients like Uber and Netflix. They are seeking an AI/ML Engineer to build and operate agentic AI systems for a major U.S. healthcare payer, focusing on automating the healthcare claims life cycle.

Responsibilities:

• Implement agents using Strands SDK (or equivalent) on Bedrock AgentCore Runtime including deployment, invocation, Memory, Identity, and Observability
• Design and build RAG architectures on Amazon Bedrock Knowledge Bases and vector stores, with prompts tuned for healthcare and claims-domain semantics
• Build and query the ontology layer knowledge graphs and graph databases (e.g., Amazon Neptune) that encode claims concepts, rules, and relationships — and wire it into agent retrieval so agents ground on accurate, connected data rather than isolated records
• Design Model Context Protocol (MCP) servers and downstream API aggregation
• Implement multi-agent orchestration patterns: sequential, parallel, and supervisor
• Build event-driven pipelines: a sync processing, Kafka producers and consumers, dead-letter queues, and retry/backoff
• Develop backend services in Python, including Lambda functions and Fast API-based REST integrations
• Manage claim state and audit trails in DynamoDB; handle PHI with KMS encryption and least-privilege IAM tied to Agent Core Identity
• Instrument agents for tracing, monitoring, and debugging via Agent Core Observability
• Ship through CI/CD with multi-environment promotion (dev → test → prod)