Responsibilities Design and deploy scalable data and AI pipelines on Azure using Databricks, Azure Data Factory, and related services Build Retrieval-Augmented Generation (RAG) systems and AI-assisted workflows that integrate with internal data sources and APIs Develop and maintain Python-based applications, microservices, and Azure Container Apps Apply prompt engineering techniques and work with LLM APIs (OpenAI, Anthropic, Azure OpenAI) to deliver reliable, production-ready AI features Implement and maintain MCP (Model Context Protocol) integrations to connect AI models with enterprise tools and data sources Participate in fine-tuning and evaluation of models; contribute to model training workflows where applicable Establish best practices for AI observability, evaluation, safety guardrails, and responsible deployment Collaborate closely with data scientists, product managers, and business stakeholders to translate requirements into engineering solutions Mentor junior engineers and contribute to architectural decisions Qualifications 3+ years of hands-on software engineering experience, with at least 1 year focused on AI/ML systems in production Strong Python proficiency - data manipulation, API development, async patterns, testing Solid experience with Azure cloud services: Azure Data Lake, Azure Container Apps, Azure Blob Storage, Azure OpenAI Service, and related tooling Experience with Databricks for large-scale data processing and ML workflows (Delta Lake, Spark, MLflow) Practical experience with RAG architectures, vector databases (e.g. Starcom has long been the professional birthplace and proving ground for marketing leaders - CEOs, CMOs, sales leaders, and technology pioneers - and we continue to drive the industry with peerless talent and relentless innovation.