Language Requirements: Professional English proficiency We are seeking a skilled Senior AI/Backend Engineer with deep expertise in Python, AI orchestration, and cloud-native backend systems to join our growing team. You will play a key role in developing a scalable, production-ready AI Voice Dispatch Assistant operating entirely within a secure AWS environment. Your work will directly impact the reliability, intelligence, and scalability of a multi-agent voice AI platform. Key Responsibilities Design, implement, and maintain a multi-agent AI system using Strands Agents SDK (BidiAgent) deployed on AWS ECS/Fargate, ensuring per-session isolation, auto-scaling, and lifecycle management of Nova 2 Sonic BidirectionalStream. Develop and maintain high-performance backend services and APIs using FastAPI, including centralized API client libraries for Member Services, Dispatch, Coverage, and Eligibility workflows. Build robust backend features such as Pydantic-based data models, field-level PII masking, audit logging, and endpoint-level caching strategies. Implement LLM orchestration and Retrieval-Augmented Generation (RAG) pipelines, including triage super-agent routing using Nova Micro and specialized sub-agent delegation. Integrate AWS Bedrock Knowledge Bases, OpenSearch Serverless, and Titan embeddings to ground AI responses using technical documentation and domain-specific knowledge. Configure security, compliance, and content protection controls, including Bedrock Guardrails, AWS Cognito authentication, FastAPI JWT middleware, and Lambda-based authorization mechanisms. Develop and manage serverless infrastructure components including API Gateway, AWS Lambda handlers, DynamoDB session state management, and ElastiCache Redis integrations. Must-Have Qualifications 5+ years of senior-level software engineering experience with a strong focus on Python development. Extensive experience building scalable, resilient backend systems and APIs, preferably using FastAPI. Strong hands‑on expertise with AI/ML concepts, including LLM orchestration, prompt engineering, and Retrieval-Augmented Generation (RAG). Deep knowledge of AWS services including ECS/Fargate, Lambda, API Gateway, DynamoDB, ElastiCache, and AWS Bedrock services such as Nova 2 Sonic and Nova Micro. Experience with multi‑agent AI architecture frameworks such as Strands Agents SDK or similar technologies. Solid understanding of authentication, security, and compliance best practices, including PII handling, prompt‑injection protection, and access control systems. Ability to collaborate effectively across distributed teams while maintaining consistent overlap with U.S. business hours. Preferred Qualifications Familiarity with OpenSearch Serverless, Titan embeddings, and AWS‑native RAG implementations. Experience designing secure, enterprise‑grade AI solutions within controlled cloud environments. Background working with healthcare, dispatch, or operational workflow automation platforms. #J-18808-Ljbffr