Azure OpenAI Engineer

About the Role:

We are looking for an experienced Azure OpenAI Engineer to design, build, and operate scalable AI platform capabilities on Microsoft Azure, with a strong focus on Azure OpenAI, Azure Kubernetes Service (AKS), Generative AI, RAG, AI agents, and multi-agent workflows.

The role will involve building reusable AI platform components, APIs, deployment frameworks, agent harnesses, governance controls, and observability capabilities that enable secure and reliable enterprise AI adoption.

Key Responsibilities:

- Lead the design, development, and deployment of enterprise AI platforms on Microsoft Azure, with a strong focus on Azure AI services and AKS.

- Build and maintain scalable, secure, and reusable platform components supporting LLM applications, RAG solutions, AI agents, and multi-agent workflows.

- Develop reusable APIs, platform services, deployment templates, reference implementations, and engineering frameworks for enterprise AI use cases.

- Build and enhance agent harnesses supporting orchestration, tool integration, memory, context and state management, policy enforcement, tracing, and exception handling.

- Design and optimize RAG pipelines, including document ingestion, embeddings, vector search, retrieval, context construction, and response generation.

- Integrate LLMs, AI services, enterprise APIs, and data sources securely and efficiently.

- Implement AI guardrails, policy controls, content safety mechanisms, and responsible AI practices.

- Build evaluation capabilities to measure AI/LLM quality, relevance, reliability, safety, and performance.

- Develop and automate CI/CD pipelines for AI applications and platform components using GitHub Actions or equivalent tools.

- Automate infrastructure provisioning and environment management using Terraform and Infrastructure as Code practices.

- Implement security validation and deployment controls across AI workloads and cloud infrastructure.

- Establish comprehensive observability, monitoring, logging, tracing, and alerting for AI applications and platform infrastructure.

- Monitor and optimize AI workloads for scalability, availability, latency, reliability, and cost.

- Collaborate with Architecture, Data Engineering, Security, DevOps, Product, and business teams to define AI platform standards, governance, and operating practices.

- Provide technical leadership in enterprise AI platform adoption and integration.

- Mentor engineering teams on AI platform development, deployment, security, and operational excellence.

- Troubleshoot complex AI platform, deployment, integration, and production issues and drive root-cause resolution.

- Stay current with Azure OpenAI, Azure AI, AKS, GenAI, agentic AI, and AI platform engineering advancements and identify opportunities for platform enhancement.

Required Skills & Experience:

- 7 - 12 years of experience in software engineering, cloud engineering, AI/ML engineering, or platform engineering.

- Strong hands-on experience with Microsoft Azure and cloud-native application development.

- Strong expertise in Azure OpenAI and enterprise Generative AI application architecture.

- Hands-on experience with AKS/Kubernetes, containers, and scalable AI workloads.

- Strong understanding of LLMs, RAG, embeddings, vector search, prompt engineering, and AI agent architectures.

- Experience building AI agents, multi-agent workflows, orchestration, tool/function calling, and stateful AI applications.

- Strong understanding of agent memory, context management, exception handling, tracing, and policy enforcement.

- Experience building and optimizing RAG and retrieval pipelines.

- Strong experience with REST APIs, microservices, enterprise integrations, and distributed systems.

- Hands-on experience with GitHub Actions or similar CI/CD platforms.

- Strong experience with Terraform / Infrastructure as Code.

- Experience implementing AI guardrails, security controls, responsible AI practices, and governance mechanisms.

- Experience with AI/LLM evaluation, monitoring, observability, logging, and tracing.

- Strong programming experience in Python and/or another modern programming language.

- Good understanding of cloud security, identity, access control, secrets management, and secure data integration.

- Strong analytical, troubleshooting, and problem-solving skills.

- Strong technical leadership, communication, stakeholder management, and mentoring capabilities.

Skills

Generative AI, Azure Kubernetes Service, Python, Terraform, RAG, OpenAI, Azure, LLM