Job Description

Required Skills for this role include:

• 5 to 7 years’ Experience in developing Python frameworks
• 3 years of experience in developing generative AI models using python and relevant frameworks.
• Hands-on experience with Microsoft Foundry (formerly Azure AI Studio) for building, deploying, and managing enterprise GenAI applications and agents.
• Experience with Azure OpenAI Service / Foundry Models for model selection, deployment, prompt engineering, inference integration, and model version management.
• Experience with Foundry Agent Service for designing, deploying, and scaling AI agents using SDKs, REST APIs, and portal-based configurations.
• Strong experience in building RAG solutions using Azure AI Search / Foundry knowledge retrieval capabilities.
• Experience with Foundry evaluation, tracing, and monitoring to assess model and agent quality, safety, and performance.
• Exposure to Foundry Tools / Azure AI Services such as Document Intelligence, Language, Speech, Translator, Vision, and Content Understanding for enterprise AI use cases.
• Familiarity with Azure RBAC, managed identities, Application Insights, CI/CD pipelines, Docker, and REST API-based deployment in Azure environments.

Desired Skills:

• Experience in developing GenAI copilots, chatbots, and agentic AI applications using Microsoft Foundry and Azure services.
• Knowledge of prompt engineering, RAG, vector search, agent orchestration, and GenAI evaluation frameworks.
• Exposure to Azure Machine Learning, Application Insights, and enterprise-grade Azure deployments.
• Knowledge of Web API, MVC, and integration of AI services into business applications.