- Role : Senior Lead Full Stack AI Engineer

- Location : Gurugram

- Required Experience : 8 -10 years

- Work Mode : WFO

Key Responsibilities :

- Lead engineering teams in designing scalable solutions for GenAI/LLM-driven applications.

- Build and deliver end-to-end full-stack solutions using ReactJS (frontend) and FastAPI (backend) for LLM-powered applications.

- Provide mentorship, code reviews, and architectural guidance to junior engineers.

- Develop responsive and dynamic UI components using React and Next.js.

- Build and integrate RESTful and GraphQL APIs for seamless system communication.

- Collaborate with product and design teams to deliver intuitive AI application interfaces.

- Design and implement Retrieval-Augmented Generation (RAG) workflows including document ingestion, chunking, embedding, indexing, and retrieval.

- Implement prompt engineering, guardrails, and evaluation strategies to improve quality, reliability, and safety of LLM outputs.

- Build agentic workflows using frameworks such as LangGraph, AutoGPT, CrewAI, or similar to automate multi-step tasks.

- Integrate and orchestrate LLM pipelines using tools such as LangChain, LlamaIndex, OpenAI APIs, or equivalent.

- Deploy and manage solutions using cloud services (AWS/Azure/GCP) and serverless components (e.g., AWS Lambda/Azure Functions/GCP Cloud Functions).

- Implement MLOps practices for AI/LLM solutions including deployment, versioning, monitoring, and observability.

- Optimize cloud infrastructure for cost, performance, and security.

- Implement CI/CD pipelines and monitoring tools

Required Skills & Expertise :

- 8-10 years of professional experience in software engineering.

- API Creation & Integration (REST, GraphQL).

- React & Next.js for modern web development.

- UI development for AI applications.

- Expertise in Generative AI, LLMs, Prompt Engineering, and RAG.

- Experience with Agentic AI frameworks (LangGraph, AutoGPT, CrewAI, or similar).

- Sound knowledge of MLOps practices including model deployment, versioning, and monitoring.

- Familiarity with LLM orchestration tools : LangChain, LlamaIndex, OpenAI, etc.

- Experience in cloud ecosystems AWS, Azure, or GCP.

- Strong knowledge of software architecture, design patterns, and scalability principles.

- Excellent problem-solving and communication skills related to AI.