Full Stack - AI Engineer

Deutsche Telekom Digital Labs; Gurugram District; On-site; INR 2,400,000 - 4,200,000; Full time

Job summary

Deutsche Telekom Digital Labs is seeking a Full Stack Agentic AI Engineer to build AI-native web apps and autonomous AI workflows. You will design responsive UIs, implement robust backends, and integrate multiple LLMs and vector DBs to deliver production-grade AI solutions.

You will own features end-to-end, develop REST APIs, and deploy on cloud platforms while monitoring performance and user experience. Strong React, Python, and AI tooling experience is essential.

Qualifications

• Experience with React.js, JavaScript/TypeScript.
• Strong Python proficiency and backend API development.
• Experience with FastAPI, Flask or Django.
• Hands-on Generative AI and LLM applications.
• Experience building RAG pipelines and semantic search.
• Knowledge of embeddings and vector databases.
• Familiarity with LangChain, LangGraph, LlamaIndex, CrewAI, AutoGen.
• Experience with AI agents and workflow orchestration.
• SQL and NoSQL databases; Docker and Kubernetes preferred.
• Cloud platforms AWS/GCP/Azure.

Responsibilities

• Build and ship AI-native web apps using React.js and Python.
• Design and develop Agentic AI workflows leveraging LLMs.
• Build RAG apps with vector databases and enterprise sources.
• Own features end-to-end from architecture to deployment.
• Develop REST APIs and backend services for AI apps.
• Integrate AI models from OpenAI, Anthropic, Gemini, or open-source LLMs.
• Work with vector DBs like Pinecone, Weaviate, Chroma, FAISS, Milvus.
• Implement prompt engineering, tool calling, and multi-agent orchestration.
• Optimize latency, cost, reliability, and scalability.
• Collaborate with product, design, and engineering teams; deploy on cloud.
• Build CI/CD pipelines and deploy on AWS, Azure, or GCP.
• Monitor AI systems for performance and quality.

Skills

React.js

JavaScript/TypeScript

HTML5/CSS3

State management

Tools

FastAPI

Flask

Django

Docker

Kubernetes

AWS

GCP

Azure

Pinecone

Weaviate

Chroma

FAISS

Milvus

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.

The core requirements for the job include the following:

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).