Frontend / GenAI Engineer

We are looking for an experienced Frontend / GenAI Engineer with strong expertise in any one of the React.js, Next.js and TypeScript, with hands-on experience in developing GenAI-powered user interfaces and LLM-based applications.

The candidate will be responsible for designing and developing modern, scalable and responsive UI/UX rich frontend applications while integrating Generative AI, LLM APIs, Azure OpenAI, Azure AI Search and AI Agent/Multi-Agent capabilities.

Key Responsibilities

• 812 years strong hands-on experience in design, develop and maintain scalable, responsive and high-performance web applications using React.js, Next.js and TypeScript.
• Build reusable, modular and maintainable frontend components and UI frameworks.
• Develop modern user experiences for AI-powered enterprise applications.
• Demonstrated experience building GenAI/LLM-powered applications or AI-enabled enterprise applications.
• Experience integrating frontend applications with LLM APIs, Azure OpenAI and/or Azure AI Search.
• Strong understanding of real-time streaming, asynchronous processing and API-driven architectures.
• Integrate frontend applications with REST APIs, JSON-based services and backend microservices.
• Handle API authentication, authorization, error handling, retries and response validation.
• Support deployment and application configuration across Microsoft Azure and/or AWS environments.
• Develop frontend interfaces for AI Agent and Multi-Agent systems.
• Integrate agent workflows, tool execution, task status and intermediate responses into user interfaces.
• Build UI capabilities for displaying agent reasoning status, tool execution status, responses and workflow progress, where appropriate.
• Exposure to AI Agents, RAG or Multi-Agent applications is highly desirable.
• Good understanding of application security, authentication, authorization and cloud deployment.
• Strong problem-solving, communication and stakeholder collaboration skills.

Good-to-Have / Want Skills

• RAG & AI Agents: Exposure to RAG, AI Agent/Multi-Agent applications, tool calling and agent workflows.
• LangChain / LangGraph: Working knowledge of LLM workflow and agent orchestration frameworks.
• LLM Integration & Streaming: Experience with LLM APIs, real-time streaming, SSE/WebSockets and asynchronous processing.
• AI Evaluation & Observability: Exposure to AI evaluation, logging, tracing, monitoring and identifying accuracy issues or abnormal behaviour.
• Cloud & DevOps: Knowledge of Azure/AWS, Docker, CI/CD and cloud-based application deployment.
• Security & Cost Optimization: Understanding of authentication, authorization, API security, token usage and GenAI cost optimization.