Azure Platform Engineer

Job Title: Microsoft Certified Azure AI Engineer with AI Foundry Exp (Onsite)

Location: Onsite in Newark, NJ

Duration: 6 Months

Azure AI Python LLMs AI Agents RAG Role Overview An Azure AI Foundry AI Engineer designs, builds, and deploys intelligent generative AI, agentic workflows, and RAG (Retrieval-Augmented Generation) applications. This role requires coding with Python, orchestrating AI models, and adhering to responsible AI standards for enterprise scalability.

• AI & Agent Development:
  Design autonomous or semi-autonomous AI agents and RAG pipelines using Azure AI Foundry (formerly Azure AI Studio).
• Testing & Evaluation:
  Implement performance and evaluation tooling (such as RAGAS or Tru Lens) to assess grounding accuracy, reduce hallucinations, and ensure model explainability.
• Infrastructure Management:
  Develop scalable AI infrastructure and maintain reusable AI components in accordance with engineering best practices (version control, observability, CI/CD).

Technical

Skills:

Proficiency in Python, prompt engineering, and utilizing frameworks like Lang Chain, Semantic Kernel, or crewAI. Python (primary language) ML frameworks:
Tensor Flow, PyTorch, Scikit-learn. Data pipelines and preprocessing. Model deployment and MLOps (e.g., MLflow, Docker, CI/CD). Machine learning, deep learning, and statistics. Data modeling and feature engineering. APIs and microservices. Cloud platforms (Azure ML, Sage Maker, Vertex AI). LLMs (GPT, Llama, etc.). RAG (Retrieval-Augmented Generation). Prompt engineering and vector databases. Ability to build AI-powered applications (chatbots, agents, copilots).

Skills:

Communication. MySQL.

Cloud

Experience:

Deep understanding of the Microsoft Azure ecosystem, including Azure OpenAI Service, Azure Machine Learning, and Microsoft Fabric.

AI Governance: Strong focus on Responsible AI and Model Context Protocol (MCP) to ensure security, privacy, and fairness in model outputs.