This role involves building and deploying AI-powered applications and systems. You will leverage Cloud AI services and on-premise solutions to deliver production-ready pipelines. A key aspect of this position is applying Generative AI (GenAI) models within solutions, potentially including deep learning, neural networks, chatbots, and image processing.

The position focuses on creating end-to-end user-facing AI products. This encompasses frontend development, backend services, AI orchestration, data integration, and deployment. You'll utilize modern tools like v0, Lovable, Bolt.new, Replit Agent, Cursor, Claude Code, or Copilot for rapid development and conversion of prototypes into robust React/TypeScript and Python services. Production ownership of shipped full-stack applications is essential.

- Design and develop user-friendly interfaces for conversational and workflow-driven AI applications. - Construct backend services, APIs, agent orchestration, and integrate tools and data sources. - Implement advanced features such as streaming, state management, approvals, and exception handling. - Integrate authentication, authorization, and enterprise systems. - Build comprehensive evaluation, telemetry, error handling, and production monitoring systems. - Optimize applications for user experience, latency, reliability, accessibility, and cost-effectiveness. - Contribute to production support and ongoing system improvements.

- Proven experience building and operating full-stack applications used by actual users. - Hands-on proficiency with modern frontend frameworks like React and TypeScript, or equivalents. - Strong skills in Python, API development, asynchronous processing, and database management. - Familiarity with LLM APIs, Retrieval-Augmented Generation (RAG), agent frameworks, streaming technologies, and structured output generation. - Experience with cloud deployment, containerization, CI/CD pipelines, identity management, security best practices, and observability tools.