Job Description
Job Description
Client: Leading Healthcare client
Location: Schaumburg, IL- Hybrid (3Days/week)
Duration: 24+ Months
What You'll Do
• Design and ship production GenAI applications: RAG pipelines, LLM-based services, and agentic workflows using tools, memory, and multi-step reasoning
• Build and operate MLOps/LLMOps pipelines — CI/CT/CD for model testing, validation, versioning, and promotion across environments
• Stand up LLM application infrastructure: gateways, orchestration layers, model routing, caching, and cost/latency optimization
• Deploy scalable, cloud-native ML services on Azure using Docker and Kubernetes
• Implement model monitoring for drift, latency, bias, and data quality, with automated retraining
• Ensure governance and compliance — lineage, reproducibility, observability, and responsible AI controls for PHI-adjacent systems
• Partner with data scientists, data engineers, and software engineers to define production AI standards
Required Qualifications
• 5+ years in machine learning or AI engineering, including production systems
• Strong Python with experience building maintainable, testable production services
• 3+ years building Generative AI / LLM applications — prompt engineering, fine-tuning, and LLM API integration
• Hands-on experience with RAG architectures and an LLM framework such as LangChain or LangGraph
• Production deployment experience on a major cloud (Azure preferred) with Docker, CI/CD, and containerized workflows
Preferred Qualifications
• Agentic AI in production — orchestration, tool use, memory, and multi-step reasoning workflows
• ML framework depth with PyTorch, TensorFlow, or Hugging Face, including model fine-tuning
• Azure-first depth: Azure Machine Learning (workspaces, compute, pipelines, jobs, endpoints) and Azure Databricks
• Kubernetes and ML lifecycle platforms such as MLflow, Kubeflow, SageMaker, or Vertex AI
• Infrastructure-as-code with Terraform and pipelines in GitHub Actions
• Streaming and data infrastructure: Spark, Kafka, MS SQL Server, NoSQL (Cassandra)
• LLM observability tooling such as LangFuse
• Proven experience optimizing LLM latency, cost, and performance at scale
• Experience in regulated environments — healthcare / HIPAA, PHI handling, and responsible AI governance.