Virtusa - Full Stack AI Engineer

We are looking for an experienced Full Stack AI Engineer with strong expertise in React.js, Node.js, Python FastAPI, and Generative AI to design, develop, integrate, and maintain scalable web applications and AI-enabled solutions.

The role combines modern full-stack engineering with RAG, GraphRAG, LLM integration, agentic workflows, intelligent applications, and distributed systems. The ideal candidate should be comfortable working across frontend, backend, data, and AI layers to build production-grade applications.

Key Responsibilities :

- Design, develop, and maintain scalable, responsive, and reusable frontend applications using React.js, JavaScript/TypeScript, HTML, and CSS.

- Design and develop backend services, APIs, and microservices using Node.js/Express and Python FastAPI.

- Build and integrate Generative AI and LLM capabilities into full-stack applications and enterprise workflows.

- Design and implement RAG and GraphRAG solutions using enterprise knowledge sources, structured and unstructured data, vector retrieval, and knowledge graphs.

- Develop retrieval pipelines covering document ingestion, chunking, embeddings, metadata, semantic search, graph-based retrieval, hybrid retrieval, and context construction.

- Work with graph and vector technologies to model entities, relationships, and knowledge required for GraphRAG applications.

- Integrate LLMs, AI services, APIs, intelligent automation, and AI agents into enterprise applications.

- Design and implement API integrations between frontend applications, backend services, databases, third-party systems, and AI platforms.

- Develop agentic workflows involving tool/function calling, orchestration, context management, and multi-step execution.

- Implement authentication, authorization, API security, input validation, error handling, and secure coding practices.

- Design efficient data-access and processing solutions using SQL and relevant database technologies.

- Optimize SQL queries, backend services, retrieval pipelines, and application performance for scale and low latency.

- Build asynchronous and distributed processing capabilities using technologies such as Redis and BullMQ.

- Implement AI evaluation and testing mechanisms to measure accuracy, relevance, reliability, latency, and retrieval quality.

- Containerize and deploy applications using Docker and cloud-native technologies.

- Participate in CI/CD, testing, release management, monitoring, and production support activities.

- Collaborate with Architects, Developers, Data Engineers, QA, Product Owners, and business stakeholders throughout the development lifecycle.

- Conduct code reviews, contribute to architecture discussions, and establish reusable software and AI engineering patterns.

- Troubleshoot complex frontend, backend, API, data, distributed-system, and AI application issues.

- Drive continuous improvement in application scalability, maintainability, reliability, and AI solution quality.

Required Skills & Experience :

- 7 - 12 years of experience in full-stack software development, with strong production engineering experience.

- Strong hands-on expertise in React.js, Node.js/Express, Python, and FastAPI.

- Strong proficiency in JavaScript/TypeScript and Python.

- Strong understanding of REST APIs, microservices, asynchronous programming, API integration, and backend architecture.

- Hands-on experience developing LLM-powered and Generative AI applications.

- Strong experience with RAG architectures, embeddings, vector search, prompt engineering, and LLM integration.

- Hands-on experience with GraphRAG, knowledge graphs, graph databases, or hybrid graph + vector retrieval.

- Good understanding of entity modelling, relationships, semantic retrieval, and knowledge representation.

- Experience with AI agents, agentic workflows, tool/function calling, or LLM orchestration.

- Hands-on experience with Redis, BullMQ, or equivalent caching and asynchronous job-processing technologies.

- Strong SQL skills, including query optimization, data modelling, and efficient data access.

- Strong understanding of distributed systems, scalability, resiliency, and performance engineering.

- Experience with Docker, cloud-native application development, Git, CI/CD, testing, and deployment.

- Good understanding of authentication, authorization, API security, and secure application development.

- Experience with AI evaluation, testing, monitoring, or observability is preferred.

- Strong analytical, debugging, and problem-solving skills.

- Good communication and cross-functional collaboration skills.

Good to Have :

- Experience with LangChain, LangGraph, LlamaIndex, or equivalent AI frameworks.

- Experience with graph databases such as Neo4j, Amazon Neptune, TigerGraph, or equivalent.

- Experience with vector databases such as Pinecone, Milvus, Weaviate, pgvector, or similar.

- Experience with OpenAI, Azure OpenAI, Anthropic, Gemini, or other enterprise LLM platforms.

- Exposure to MCP, AI agents, LLM observability, and evaluation frameworks.

- Experience with AWS, Azure, or GCP, Kubernetes, and cloud-native deployment.

- Experience building AI-powered enterprise search, knowledge discovery, recommendation, or decision-support applications.