We are seeking a Senior AI Engineer / Applied AI Scientist with deep expertise in Generative AI, LLMs, and Azure cloud ecosystems to design, build, and scale intelligent systems. This role goes beyond traditional backend engineering and focuses on end-to-end AI solution development, including: Multi-agent LLM systems RAG pipelines and evaluation frameworks Advanced search, retrieval, and reasoning systems Scalable AI/ML pipelines in cloud environments You will work closely with Engineering Leads, Data Scientists, AI Engineers, and stakeholders to deliver high-impact AI-driven products. Key Responsibilities

1. AI/LLM Engineering & RAG Systems Design and build end-to-end RAG pipelines (data ingestion → embedding → retrieval → inference) Develop LLM-powered applications and multi-agent systems (ReAct, LangChain, LangGraph) Implement: Vector indexing & semantic search (Azure AI Search, VectorDBs) Hybrid retrieval (vector + keyword search) Prompt engineering and LLM orchestration Build automated evaluation frameworks (RAGAS, ROUGE, etc.) for model quality and performance
2. Backend & API Development Develop scalable microservices and APIs using Python (FastAPI/Flask preferred) Build services for: Data ingestion and normalization Embedding pipelines Inference orchestration Feedback and evaluation systems Integrate LLM services with enterprise data systems and APIs
3. Data Engineering & Pipelines Design and optimize pipelines using: Azure Data Factory, Azure Functions, EventHub/Service Bus Data lakes, warehouses, and vector stores Handle: Structured + unstructured data ingestion Document processing, chunking, and metadata enrichment Implement secure data handling, PII masking, and governance controls
4. Azure AI & Cloud Engineering Build and deploy solutions using: Azure OpenAI / Azure AI Studio Azure Cognitive Search Azure ML / Databricks / Fabric Implement: Secure access (Azure AD, Managed Identity, Key Vault) Scalable distributed systems for inference workloads
5. MLOps, DevOps & Productionization Develop and maintain: CI/CD pipelines (Azure DevOps, GitHub Actions) Infrastructure as Code (Terraform) Implement: Model monitoring, evaluation, and retraining pipelines Performance tuning and load testing for LLM systems Containerization & orchestration using Docker/Kubernetes
6. Architecture & Technical Leadership Contribute to: Architecture diagrams (C4, sequence diagrams) API contracts and system design Provide technical guidance on: GenAI solution design patterns Agentic AI systems and orchestration strategies Collaborate cross-functionally with stakeholders and client teams Required Skills & Experience Core Technical Skills 6+ years of experience in AI/ML Engineering or Backend Development Strong Python expertise (FastAPI, ML/AI frameworks) Deep experience with: LLMs, Generative AI, NLP RAG architectures and vector databases Hands-on experience with: Azure AI stack (Azure OpenAI, Cognitive Search, AI Studio) Experience with: LangChain / LangGraph / Agent frameworks Embedding pipelines and semantic search Systems & Engineering Strong understanding of: Distributed systems and microservices Event-driven architectures and async workflows Experience with: REST APIs, backend systems, and cloud-native design Databases (SQL, NoSQL, VectorDBs) MLOps & Deployment Experience with: Model deployment, monitoring, and lifecycle management CI/CD and containerization (Docker/K8s) Familiarity with evaluation metrics for LLM systems (RAGAS, ROUGE, etc.) Nice to Have Experience with: Multi-agent systems (ReAct, autonomous agents) Knowledge graphs / GraphRAG SharePoint Graph API & enterprise integrations Background in: Financial services, insurance, healthcare, or enterprise analytics Experience leading AI teams or large-scale projects