Full Stack - AI Engineer

Deutsche Telekom Digital Labs; Gurugram District; On-site; INR 1,500,000 - 2,000,000; Full time

Job summary

Deutsche Telekom Digital Labs is seeking a Full Stack Agentic AI Engineer to innovate with AI-native products. The role involves building web applications with React.js and Python while leveraging Generative AI and LLM technologies. You will design and deploy scalable systems, integrate various AI models, and collaborate closely with product teams.

The ideal candidate should be proficient in modern front-end and back-end technologies, familiar with API development, and have hands-on experience with various AI frameworks and tools.

Qualifications

• Strong experience with modern web application development using React.js.
• Hands-on experience with deployments and building scalable cloud applications.
• Expertise in backend development with Python frameworks.

Responsibilities

• Build and ship AI-native web applications using React.js and Python.
• Design and develop Agentic AI workflows leveraging LLMs and autonomous agents.
• Integrate AI models from major providers like OpenAI and Anthropic.
• Work with vector databases to support AI applications.
• Monitor AI systems for performance and reliability.

Skills

React.js

Python

JavaScript/TypeScript

AI and LLM applications

Docker and Kubernetes

Tools

FastAPI

Flask

Django

AWS

Azure

GCP

Job description

We are looking for a Full Stack Agentic AI Engineer who is passionate about building the next generation of AI-native products. This role combines modern full-stack development with cutting-edge Generative AI technologies to create intelligent, autonomous applications from 01 and scale them into production. You will work across the entire stack, designing responsive user interfaces, building robust backend services, integrating Large Language Models (LLMs), developing Agentic AI workflows, and deploying scalable AI systems that solve real business problems.

Responsibilities

• Build and ship AI-native web applications using React.js and Python.
• Design and develop Agentic AI workflows leveraging LLMs and autonomous agents.
• Build Retrieval-Augmented Generation (RAG) applications using vector databases and enterprise knowledge sources.
• Own product features end-to-end from architecture and development to deployment, monitoring, and optimisation.
• Develop REST APIs and backend services to support AI-powered applications.
• Integrate AI models from providers such as OpenAI, Anthropic, Gemini, or open-source LLMs.
• Work with vector databases such as Pinecone, Weaviate, Chroma, FAISS, or Milvus.
• Implement prompt engineering, tool calling, memory management, and multi-agent orchestration.
• Optimize AI applications for latency, cost, reliability, and scalability.
• Collaborate with product managers, designers, and engineering teams to deliver production-ready solutions.
• Build CI/CD pipelines and deploy applications on cloud platforms such as AWS, Azure, or GCP.
• Monitor AI systems for performance, hallucinations, and overall user experience.

Core Requirements

Frontend

• Strong experience with React.js, JavaScript/TypeScript.
• HTML5 CSS3 and responsive UI development.
• State management (Redux, Context API, Zustand, etc.)

Backend

• Strong proficiency in Python.
• Experience with FastAPI, Flask, or Django.
• API development and microservices architecture.

AI and LLMs

• Hands-on experience with Generative AI and LLM applications.
• Experience building RAG pipelines.
• Knowledge of embeddings and semantic search.
• Familiarity with LangChain, LangGraph, LlamaIndex, CrewAI, AutoGen, or similar frameworks.
• Experience with AI agents and workflow orchestration.

Databases and Infrastructure

• SQL and NoSQL databases.
• Vector databases (Pinecone, Chroma, Weaviate, FAISS, Milvus).
• Docker and Kubernetes (preferred).
• Cloud platforms (AWS/GCP/Azure).