Senior AI Engineer - Generative AI & Azure AI Platform

We are looking for a Senior AI Engineer to design, build, and operate production-grade Generative AI solutions on the Microsoft Azure AI ecosystem. You will be the technical anchor for our GenAI initiatives, owning the end-to-end lifecycle: from foundation model selection and prompt/RAG architecture through deployment, MLOps, security hardening, and continuous evaluation. This is a hands-on senior role. You will set technical direction, mentor engineers, and work directly with product, data, security, and platform teams to move AI use cases from prototype to reliable, governed, cost-efficient services.

• Architect and build LLM-powered applications (RAG, agents, copilots, document intelligence, content understanding, conversational systems) using Azure AI Foundry, Azure OpenAI, and the broader Azure AI and data portfolio

. • Design retrieval pipelines with Azure AI Search (vector, hybrid, and semantic ranking), including chunking, embedding, indexing, and relevance tuning strategies.

• Evaluate, fine-tune, and deploy foundation and open-source models (e.g., GPT, Phi, Llama, Mistral, Kimi, GLM) through Azure AI Foundry model catalog and Azure Machine Learning.

• Implement prompt engineering, orchestration frameworks (Semantic Kernel, LangChain, Prompt Flow, or equivalent), and structured evaluation of model quality, groundedness, and safety.

• Build and maintain MLOps/LLMOps pipelines on Azure ML, Github Enterprise: experiment tracking, model registry, CI/CD for models and prompts, automated evaluation, monitoring, and drift/cost management.

• Expose AI capabilities as scalable microservices (Azure Kubernetes Service, Azure Container Apps, Azure Functions, API Management), with attention to latency, throughput, resilience, and cost.

• Establish observability for AI systems: tracing, token/cost telemetry, quality metrics, and feedback loops.

• Apply Responsible AI and AI security practices: content safety filters, prompt-injection and jailbreak mitigation, data-leakage controls, PII handling, and red-teaming.

• Implement secure architectures using Azure identity (Entra ID, managed identities), private endpoints, Key Vault, network isolation, and data residency controls.

• Contribute to AI governance standards, model risk documentation, and compliance requirements.

• Define reference architectures, coding standards, and reusable components for GenAI workloads.

• Mentor and review the work of other engineers; lead design discussions and technical decision-making.

• Partner with stakeholders to translate business problems into feasible, measurable AI solutions and communicate trade-offs clearly.

• Stay current with the rapidly evolving model and tooling landscape and bring practical recommendations to the team.

• 8–10+ years of overall experience in AI, machine learning, and data engineering, with a strong track record of delivering production systems.

• Minimum 2–3 years of hands-on experience with Azure AI Foundry (formerly Azure AI Studio) and Azure OpenAI Service, including deploying and operating GenAI applications in production.

• Deep expertise across the Azure AI ecosystem: Azure Machine Learning, Azure AI Search, Azure AI Services (Document Intelligence, Language, Speech, Vision), Fabric and Azure AI Content Safety.

• Strong understanding of LLMs and foundation models: architectures, tokenization, context management, embeddings, fine-tuning (LoRA/PEFT), quantization, and evaluation methods.

• Practical experience with open-source models and frameworks (Hugging Face, Llama, Mistral, Phi, vLLM/ONNX Runtime or similar serving stacks).

• Proven MLOps/LLMOps experience: CI/CD, model versioning, automated testing and evaluation, monitoring, and rollback strategies.

• Experience designing and building microservices and APIs (containers, Kubernetes, REST/gRPC, event-driven patterns) with Azure DevOps or GitHub Actions.

• Demonstrated knowledge of AI security and Responsible AI: threat modeling for LLM applications (OWASP Top 10 for LLMs), data protection, access control, and safety guardrails.

• Working experience with at least one other cloud provider (AWS or GCP) and their AI/ML services (e.g., Amazon Bedrock, SageMaker, Vertex AI).

• Expert-level Python; solid software engineering fundamentals (testing, code review, design patterns, performance optimization).

• Strong data foundations: SQL, data pipelines, data modeling, and familiarity with Azure data services (Data Factory, Databricks, Synapse, Fabric, Cosmos DB, or equivalent).

• Excellent communication skills with the ability to explain complex AI concepts to technical and non-technical audiences.

• Microsoft certifications: AI-102 (Azure AI Engineer Associate), DP-100 (Azure Data Scientist Associate), or AZ-305.

• Experience with agentic AI patterns, multi-agent orchestration, and tool/function calling (Azure AI Agent Service, Semantic Kernel agents, AutoGen, or similar).

• Experience with vector databases beyond Azure AI Search (e.g., Cosmos DB vector search, PostgreSQL pgvector, Pinecone, Weaviate).

• Background in NLP, computer vision, or speech systems prior to the GenAI era.

• Experience with model evaluation and observability tooling (Azure AI evaluation SDK, Prompt Flow evaluations, Langfuse, MLflow, Weights & Biases).

• Familiarity with regulatory and compliance frameworks relevant to AI (GDPR, ISO/IEC 42001, NIST AI RMF, EU AI Act, or regional data protection regulations).

• Experience operating in regulated industries (financial services, healthcare, government) or large-enterprise environments.

• Contributions to open-source projects, publications, or technical community engagemen

• Ownership and delivery focus in ambiguous, fast-moving environments

• Systems thinking: balancing model quality, latency, cost, security, and maintainability

• Pragmatism about when GenAI is (and is not) the right tool

• Mentorship and collaborative technical leadership