GenAI Engineer - Azure OpenAI & AWS Bedrock

Job Summary: We are seeking a GenAI Engineer with hands-on experience in Azure OpenAI and AWS Bedrock to design, develop, and deploy scalable Generative AI solutions. The role focuses on building Retrieval-Augmented Generation (RAG) pipelines, integrating Large Language Models (LLMs) into enterprise applications, and ensuring performance, security, and cost efficiency in AI-driven systems. Location: Malvern, PA - Onsite Key Responsibilities: Design, develop, and implement Retrieval-Augmented Generation (RAG) pipelines, including document ingestion, chunking, and embedding generation. Configure, manage, and optimize vector databases for semantic and hybrid search performance. Securely integrate Large Language Model (LLM) APIs into enterprise applications and workflows. Develop and manage prompt templates and context-handling strategies to ensure consistent and accurate LLM responses. Implement monitoring and logging for LLM usage, performance, latency, and cost tracking. Build reusable AI components, frameworks, and SDKs to enable AI integration across multiple business use cases. Required Skills & Experience: Strong hands-on experience with Azure OpenAI services. Experience working with AWS Bedrock and related AWS AI services. Proficiency in Python for AI/ML and backend development. Experience designing and deploying RAG architectures . Knowledge of vector databases and embedding-based search solutions. Experience integrating LLM APIs into applications securely. Competencies: Strong analytical and problem-solving skills. Ability to design scalable and reusable AI solutions. Attention to performance, security, and cost optimization. Strong communication skills and ability to collaborate with cross-functional teams. Preferred Skills: Experience with hybrid cloud AI architectures (Azure + AWS). Familiarity with MLOps, observability, and cost-governance practices for GenAI solutions. Experience building AI SDKs or shared AI platforms.