AI & Analytics Engineer
OpenBI • Delhi
AI & Analytics Engineer Location: Delhi / NCR | Experience: 3–5 Years | Type: Full-time About OpenBI OpenBI is a data intelligence and analytics consultancy building governed data platforms and applications for enterprise clients, primarily in regulated industries. The team is small, senior and AI-first, with strong emphasis on engineering ownership, quality and production outcomes. About the Role We are looking for an AI & Analytics Engineer for a client-facing role combining Microsoft Fabric data platform engineering with application and AI engineering. You will help clients modernize fragmented Power BI environments into governed data platforms using ingestion pipelines, medallion lakehouse architecture, Direct Lake semantic models and thin reports. You will also build production applications, workflow tools, intelligence platforms and AI-driven automation across backend, frontend, data, authentication and deployment. Key Responsibilities Build full and incremental data ingestion pipelines in Microsoft Fabric from APIs, databases, files and document stores. Implement Delta-based Bronze, Silver and Gold medallion architecture. Build star schemas, SCD Type 2, surrogate keys and maintain documented data grain. Develop and manage Power BI semantic models, DAX measures, relationships and row-level security. Rebuild reports on governed semantic models and perform data validation/reconciliation. Build production web applications including APIs, databases, frontend, authentication and role-based access. Deploy and operate applications on AWS, including CI/CD, networking, logging, monitoring and cost control. Optimize application performance through query tuning, caching, pagination and payload optimization. Implement application security, authorization, input validation, secrets management and dependency hygiene. Build AI automation using agent orchestration, MCP servers, retrieval pipelines and evaluation frameworks. Requirements 3–5 years of experience in modern data platforms. Strong Microsoft Fabric experience, or Azure data engineering using ADF, Databricks/Synapse and PySpark. Strong knowledge of medallion architecture, dimensional modelling, star schemas, SCD Type 2 and incremental processing. Hands-on Power BI semantic modelling, including DAX, relationships and row-level security. Experience owning semantic models, not just creating reports and visualizations. Experience delivering at least one application end-to-end into production. Hands-on AWS experience with compute, storage, databases, networking, IAM and CI/CD. Strong Python, SQL and PySpark skills. Experience with REST APIs, authentication, pagination, retries and scheduling. Practical application performance and security experience. Experience using AI coding agents such as Claude Code, Cursor, Codex or equivalent. Strong Git practices including branching, pull requests and code reviews. Excellent written English and client-facing documentation skills. Preferred Qualifications DP-600 / DP-700, Databricks Data Engineer or AWS certifications. Experience with Fabric Dataflows Gen2, Data Activator, capacity behaviour and F-SKU sizing. RAG pipelines, MCP servers, multi-agent orchestration and AI evaluation. Production React and TypeScript experience. Infrastructure as code, containers or serverless experience. Experience across AWS and Azure, enterprise identity/access or regulated environments. Cloud/on-premise to lakehouse migration experience.
