We are seeking a highly skilled Senior Agentic AI Engineer to design, develop, and deploy production-grade agentic AI systems on Azure cloud infrastructure. The ideal candidate will have extensive experience building autonomous AI agents, deploying complex AI solutions to production, and implementing robust CI/CD pipelines.

Key Responsibilities

Design and develop sophisticated agentic AI systems capable of autonomous decision-making and task execution

Architect and implement production-grade AI solutions using Azure services (Azure Functions, Azure OpenAI, Azure Cognitive Services, etc.)

Build and maintain CI/CD pipelines using Azure DevOps and/or GitHub Actions for automated testing and deployment

Develop scalable data processing workflows using Azure Databricks and Apache Spark

Implement comprehensive testing strategies for AI applications including unit tests, integration tests, and performance testing

Optimize AI agent performance, reliability, and cost-efficiency in production environments

Design and implement monitoring, logging, and observability solutions for AI systems

Mentor junior engineers and lead technical discussions on AI architecture and best practices

Collaborate with cross-functional teams to integrate AI agents into existing systems

Implement security best practices including managed identities, Key Vault integration, and RBAC

Azure certifications (Azure AI Engineer Associate, Azure Solutions Architect)

Experience with microservices architecture

Knowledge of MLOps practices and tools (MLflow, Azure ML Pipelines)

Experience with vector databases and semantic search

 Roles: Data Platform Engineer and responsibilities are 

Design, develop, and deploy AI/ML solutions for real-world applications.

Build, fine-tune, and optimize Large Language Models (LLMs) and Generative AI applications.

Develop Retrieval-Augmented Generation (RAG) pipelines using vector databases and embedding models.

Design and implement multi-agent AI systems for complex workflows.

Develop NLP solutions including text classification, summarization, question answering, and information extraction.

Create and optimize prompts and prompt engineering strategies for LLM-based applications.

Build scalable machine learning pipelines for training, evaluation, and deployment.

Develop AI applications using frameworks such as PyTorch, TensorFlow, Scikit-learn, and Hugging Face Transformers.

Integrate AI services with REST APIs and enterprise applications.

Design, implement, and maintain comprehensive testing frameworks for AI applications.

Monitor AI model performance, application health, and production environments using tools such as Grafana, Application Insights, and Log Analytics.

Analyze model performance, identify bottlenecks, and improve inference efficiency and accuracy.

Debug complex distributed AI systems and resolve production issues.

Apply software engineering best practices, including clean code, SOLID principles, and design patterns.

Collaborate with cross-functional teams to translate business requirements into AI solutions.

Document AI models, workflows, and deployment processes.

Stay current with advancements in Generative AI, LLMs, NLP, and machine learning technologies.