Note: The job is a remote job and is open to candidates in USA. MatchPoint Solutions is a fast-growing global IT and engineering services firm that delivers innovative technology solutions to leading enterprises. The AI/ML Engineer – Agentic AI Builder will develop and deploy agentic AI solutions using AWS Bedrock, RAG architectures, knowledge graphs, MCP servers, and multi-agent orchestration. The role also involves building Python and AWS backend services, event-driven pipelines, secure cloud architectures, observability, and CI/CD deployments.
Responsibilities
- Implement AI agents using Strands SDK (or equivalent) on AWS Bedrock AgentCore Runtime, including deployment, invocation, memory, identity, and observability
- Design and build Retrieval-Augmented Generation (RAG) architectures using Amazon Bedrock Knowledge Bases and vector databases
- Build and maintain ontology-backed knowledge graphs and graph databases (e.g., Amazon Neptune) to enable accurate AI reasoning and contextual retrieval
- Design and develop Model Context Protocol (MCP) servers and downstream API integrations
- Implement multi-agent orchestration patterns, including sequential, parallel, and supervisor models
- Build event-driven processing pipelines using Kafka, asynchronous messaging, dead-letter queues (DLQs), and retry mechanisms
- Develop backend services using Python, AWS Lambda, and FastAPI-based REST APIs
- Manage application state and audit trails using DynamoDB while implementing secure data handling with AWS KMS encryption and least-privilege IAM
- Instrument AI agents for tracing, monitoring, and debugging using AgentCore Observability
- Deploy applications through CI/CD pipelines with multi-environment promotion (Development → Test → Production)
Skills
- • 5+ years of AI/ML design and development experience
- • 2+ years of hands-on experience building Agentic AI solutions
- • Strong experience with Amazon Bedrock, including model invocation, prompt engineering, and Retrieval-Augmented Generation (RAG)
- • Hands-on experience with AWS Bedrock AgentCore Runtime, including agent deployment, invocation, memory, identity, observability, gateway, and registry
- • Experience implementing multi-agent orchestration patterns (sequential, parallel, supervisor) and designing Model Context Protocol (MCP) servers
- • Experience designing ontology-backed AI knowledge graphs using graph databases such as Amazon Neptune, Neo4j, RDF/OWL, with query languages including SPARQL, Gremlin, or Cypher
- • Strong Python development experience, including Kafka producers/consumers, AWS Lambda, FastAPI, and REST API integrations
- • Experience building event-driven architectures with asynchronous pipelines, DLQs, and retry/backoff strategies
- • Hands-on experience with AWS services including EKS, Lambda, S3, SQS, EventBridge, DynamoDB, Aurora RDS, CloudWatch, and Step Functions
- • Experience with Infrastructure as Code (Terraform) and CI/CD pipelines using GitHub Actions
- • Strong understanding of secure cloud architecture, encryption, IAM best practices, and compliant data processing in regulated environments
- • Experience in the healthcare claims or insurance domain
- • Strong LLM prompt engineering experience for domain-specific AI applications
- • Experience with Kiro for specification-driven development, AI-assisted code generation, Infrastructure as Code generation, and CI/CD scaffolding
Company Overview
Company H1B Sponsorship