AI Data Engineer II

Key Responsibilities

Generative AI & Agent Development

• Design, develop, and deploy AI agents using frameworks such as LangChain, LangGraph, AutoGen, CrewAI, Semantic Kernel, or Microsoft Copilot Studio.
• Build and optimize Retrieval-Augmented Generation (RAG) solutions using vector databases.
• Fine-tune prompts and develop prompt engineering strategies to improve AI agent performance.
• Integrate AI agents with enterprise applications, APIs, databases, and business workflows.
• Develop multi-agent systems capable of performing autonomous and semi-autonomous business tasks.
• Monitor, evaluate, and enhance agent performance, reliability, and security.

Data Analytics & Engineering

• Collect, process, transform, and analyze large datasets from multiple sources.
• Develop dashboards and reports using Power BI, Tableau, or similar BI tools.
• Design and maintain data pipelines for analytics and AI model consumption.
• Perform exploratory data analysis (EDA) and generate actionable business insights.
• Implement data quality, governance, and security best practices.
• Collaborate with stakeholders to identify KPIs and measure business outcomes.

AI & Machine Learning

• Utilize LLMs such as OpenAI GPT, Azure OpenAI, Anthropic Claude, Google Gemini, or open-source models.
• Implement model evaluation frameworks and AI governance practices.
• Develop scalable AI solutions using cloud platforms.
• Ensure responsible AI principles, compliance, and ethical AI deployment.

Required Qualifications

• Bachelor's or masters degree in computer science, Data Science, Artificial Intelligence, Engineering, or related field.
• 3+ years of experience in AI/ML, data analytics, or software development.
• •Strong programming skills in Python and SQL.
• Experience with LLMs, GenAI applications, and agentic AI frameworks.
• Hands-on experience with Azure OpenAI, OpenAI API, LangChain, LangGraph, or Semantic Kernel.
• Experience with Power BI, Tableau, SQL Server, Snowflake, Databricks, or Azure Data Services.
• Understanding of vector databases such as Pinecone, Weaviate, FAISS, ChromaDB, or Azure AI Search.
• Knowledge of REST APIs, microservices, and cloud-native architectures.

Preferred Qualifications

• Experience with Microsoft Copilot Studio, Azure AI Foundry, Azure Machine Learning, or Azure Data Factory.
• Knowledge of MLOps/LLMOps practices and CI/CD pipelines.
• Experience with Kubernetes, Docker, and cloud deployment.
• Familiarity with data governance, AI security, and compliance frameworks.
• Microsoft Azure or AI-related certifications are highly desirable.