Data Science - Agentic AI

Job Summary The Data Science - Agentic AI role focuses on designing, building, and deploying agentic AI solutions using agent frameworks and protocols in cloud-native environments. The position requires hands-on expertise with agentic architectures, vector embeddings, prompt and context engineering, and scalable deployments on Azure. The role will work across the full lifecycle—from design through production—leveraging Azure services, modern programming languages, and high-performance data systems to deliver robust, scalable AI applications. Key Responsibilities Design and implement agentic AI systems using A2A agent frameworks and the MCP protocol. Build and optimize vector embedding workflows, prompt engineering, and context engineering for production-grade AI applications. Develop services and tooling in at least two programming languages (Python, Java, Go) to support agent orchestration, retrieval, and inference. Deploy and operate AI solutions on Azure Cloud with a focus on reliability, scalability, cost efficiency, and security. Integrate and manage data layers including Azure AI Search, Redis, and Cosmos DB; leverage Blob Storage and Iceberg where applicable. Design, build, and manage Azure Functions and Azure Container Apps for event-driven and containerized workloads. Apply cloud-native architectural patterns to ensure performance optimization, observability, and autoscaling. Collaborate with cross-functional teams to translate requirements into production-ready agentic solutions. Required Qualifications 8+ years of experience in AI/ML or software engineering with hands-on work in agentic AI systems. Practical experience with Agentic Layer A2A frameworks and MCP protocol. Expertise in vector embeddings, prompt engineering, and context engineering. Strong programming skills in at least two of: Python, Java, Go. Proficiency deploying solutions on Azure Cloud. Experience with databases such as Azure AI Search, Redis, and Cosmos DB. Proven ability to design and manage Azure Functions and Azure Container Apps. Strong knowledge of cloud-native architecture, scalability, and performance optimization. Preferred Qualifications Experience with Azure Blob Storage and Apache Iceberg. Background in production observability (metrics, logs, traces) and performance tuning for AI workloads. Experience with governance and security best practices for AI systems (e.g., secrets management, role-based access, network controls).