Python Engineer - Agentic AI LLMs, RAG architectures

Vibehackers; Hyderabad; On-site; INR 1,200,000 - 2,400,000; Full time

Job summary

Vibehackers in Hyderabad seeks a client-facing Python Engineer to design, build, and deploy agentic AI workflows and enterprise apps using LLMs, RAG, embeddings, and prompt engineering while integrating modern AI frameworks and cloud deployment practices.

You will work with OpenAI, LangChain, LangGraph, and LlamaIndex, delivering REST APIs and microservices deployed on Docker/Kubernetes across cloud platforms.

Qualifications

• Proficiency in Python and modern AI frameworks.
• Experience with generative AI, agentic AI, and LLMs.
• Familiarity with OpenAI APIs, LangChain, LangGraph, LlamaIndex.
• Knowledge of prompt engineering, embeddings and RAG.
• Experience with REST APIs and microservices; Docker/Kubernetes.

Responsibilities

• Develop AI-powered enterprise applications using Python and modern AI frameworks.
• Design and implement agentic AI workflows and intelligent automation solutions.
• Build solutions with LLMs, RAG architectures, embeddings, and prompt engineering.
• Integrate OpenAI, LangChain, LangGraph, and LlamaIndex into enterprise solutions.
• Develop REST APIs and microservices to expose AI capabilities.
• Deploy AI applications using Docker, Kubernetes, and cloud platforms.
• Participate in CI/CD pipelines, MLOps, testing, and production deployments.
• Collaborate with Data Scientists, Product Teams, and Solution Architects.

Skills

Generative AI

Agentic AI

Prompt engineering

REST APIs

CI/CD

MLOps

Client collaboration

Tools

Python

OpenAI APIs

LangChain

LangGraph

LlamaIndex

TensorFlow

PyTorch

Keras

Docker

Kubernetes

Azure

AWS

GCP

GitHub

Job description

Python Engineer - Agentic AI LLMs, RAG architectures

Building with LLMs, RAG, and agentic AI frameworks (LangChain, LangGraph, LlamaIndex) — directly working with AI dev tools.

About the Role

Client-facing Python Engineer to design, build, and deploy agentic AI workflows and enterprise applications using LLMs, RAG architectures, embeddings, and prompt engineering. Integrate OpenAI and modern AI frameworks, implement REST APIs/microservices, and deploy solutions on Docker/Kubernetes across cloud platforms.

Job Description

Role

We are hiring a client-facing Python Engineer to develop agentic AI workflows and AI-powered enterprise applications. The role focuses on building solutions that leverage large language models (LLMs), retrieval-augmented generation (RAG), embeddings, and prompt engineering while integrating modern AI frameworks and cloud deployment practices.

Key Responsibilities

• Develop AI-powered enterprise applications using Python and modern AI frameworks.
• Design and implement agentic AI workflows and intelligent automation solutions.
• Build solutions using LLMs, RAG architectures, embeddings, and prompt engineering techniques.
• Integrate OpenAI, LangChain, LangGraph, and LlamaIndex into enterprise solutions.
• Develop REST APIs and microservices to expose AI capabilities.
• Deploy AI applications using Docker, Kubernetes, and cloud platforms (Azure, AWS, GCP).
• Participate in CI/CD pipelines, MLOps implementation, testing, and production deployments.
• Collaborate with Data Scientists, Product Teams, and Solution Architects.

Requirements

• Proficiency in Python.
• Experience with generative AI, agentic AI, and large language models.
• Familiarity with OpenAI APIs, LangChain, LangGraph, and LlamaIndex.
• Knowledge of prompt engineering, embeddings, and RAG architecture.
• Experience with ML frameworks such as TensorFlow, PyTorch, or Keras.
• Experience building REST APIs and microservices.
• Experience with Docker and Kubernetes.
• Experience deploying to cloud platforms (Azure, AWS, GCP).
• Experience with GitHub and version control workflows.

Skills

Python Generative AI Agentic AI Prompt Engineering REST APIs Microservices CI/CD MLOps Testing Production Deployment Collaboration Client-facing