MLOps Engineer

We are building an enterprise\-scale, Azure\-native **Document Intelligence and Retrieval\-Augmented Generation (RAG)** platform designed to ingest, classify, extract, enrich, and serve knowledge from large volumes of structured and unstructured data (SharePoint, PDFs, emails, and more). We are seeking a highly skilled **MLOps Engineer** to operationalize, scale, and govern ML/LLM pipelines across this ecosystem. This role is critical in ensuring the reliability, reproducibility, security, and performance of AI workloads powered by Microsoft Azure and Azure OpenAI Service. **Responsibilities:** **1\. ML/LLM Pipeline Operationalization** * Productionize end\-to\-end pipelines across: * Data ingestion (Graph API, Azure Data Factory) * Document classification (Azure Document Intelligence, LLM\-based classifiers) * Data extraction (OCR \+ LLM parsing) * Data enrichment (embeddings, metadata tagging) * Retrieval (vector and hybrid search) * Build scalable workflows using: * Azure Data Factory * Azure Functions **2\. LLMOps \& RAG System Management** * Deploy, monitor, and optimize RAG pipelines using: * Azure OpenAI Service * LangChain * Optimize vector search using: * Azure AI Search **3\. Lifecycle Management** * Implement CI/CD pipelines for: * Prompt and configuration changes * Data schema evolution * Work with: * Azure Machine Learning * GitHub Actions / Azure DevOps **4\. Data \& Feature Pipeline Reliability** * Ensure high\-quality data ingestion from: * SharePoint, APIs, batch uploads * Manage: * Schema drift * Data validation * Metadata consistency * Work with storage solutions: * Azure Blob Storage * Azure Cosmos DB **5\. Monitoring, Observability \& Quality** * Build monitoring systems for: * Pipeline failures * Latency (retrieval \& generation) * Token usage and cost tracking * Data and embedding drift * Utilize: * Azure Monitor * Log Analytics * Application Insights **6\. Security, Compliance \& Governance** * Enforce enterprise\-grade controls: * RBAC, private endpoints, VNet isolation * Encryption via Azure Key Vault * Ensure compliance with: * SOC2, data residency, audit logging * Implement safe AI practices: * Guardrails for LLM outputs * PII handling and redaction **7\. Performance \& Cost Optimization** * Optimize: * LLM usage (prompt efficiency, caching) * Embedding storage and retrieval latency * Implement: * Autoscaling strategies * Cost monitoring dashboards * Tune: * Chunk sizes, retrieval depth, hybrid search weights **8\. Collaboration \& Enablement** * Collaborate with: * Data Engineers (ingestion pipelines) * AI Engineers (models, prompting) * Backend teams (API layer) * Enable teams through: * Reusable MLOps templates * Documentation and best practices **Qualifications:** * 6\+ years of experience in MLOps, ML Engineering, or Platform Engineering * Strong expertise in the Microsoft Azure ecosystem * Proficiency in Python (pipelines, orchestration, APIs) * Hands\-on experience with: * CI/CD for ML systems * Containerization (Docker, Kubernetes) **Preferred (LLM / RAG Experience)** * Experience with: * Azure OpenAI Service or similar platforms * LangChain * Strong understanding of: * Embeddings and vector databases * Prompt engineering lifecycle * RAG evaluation techniques Location: LHR/ISB/KHI