О компании
This position is listed on behalf of a partner company, who manages all applications and next steps.
Обязанности
- Design and implement production-ready RAG architectures using Azure OpenAI, Azure AI Search, and related Generative AI technologies.
- Develop robust backend APIs and services that support scalable AI-powered applications.
- Architect, deploy, and optimize Azure serverless solutions using technologies such as Azure Functions, Logic Apps, and Container Apps.
- Build and maintain scalable data pipelines supporting indexing, embedding generation, and retrieval workflows.
- Design secure and reliable system architectures focused on performance, scalability, availability, and maintainability.
- Implement CI/CD pipelines for AI applications using Azure DevOps or GitHub Actions to improve deployment efficiency.
- Apply Infrastructure as Code practices using Terraform or Bicep to automate cloud infrastructure management.
- Collaborate with frontend developers, data engineers, AI specialists, and stakeholders to deliver complete Generative AI solutions.
- Ensure security, governance, compliance, and best practices are integrated throughout the development lifecycle.
Требования
- Proven experience designing and deploying production-grade Retrieval-Augmented Generation (RAG) solutions.
- Strong understanding of Large Language Models (LLMs), embeddings, vector databases/search, prompt engineering, and AI application architectures.
- Hands-on experience with Azure AI services, including Azure OpenAI and Azure AI Search.
- Experience designing and implementing serverless architectures using Azure Functions, Azure Container Apps, and Azure App Services.
- Strong knowledge of Azure Storage, Key Vault, networking, identity management, and cloud security principles.
- Strong backend development skills with proficiency in Python, Java, or Node.js.
- Experience building REST APIs, microservices, and scalable backend systems.
- Solid understanding of CI/CD practices, including Azure DevOps or GitHub Actions.
- Experience with Docker, Kubernetes, Terraform, or Bicep is highly valuable.
- Familiarity with agentic AI workflows, AWS services, consulting environments, or deploying AI systems in regulated industries is a plus.
- Strong system design, problem-solving, communication, and collaboration skills.
Условия
- Remote opportunity for candidates based in India.
- Opportunity to work on advanced Generative AI and cloud-native engineering projects.