Python AI Engineer-Gurgaon

Kezan Consulting; Dadri, Gurugram District, Delhi; Hybrid; INR 2,500,000 - 4,500,000; Full time

Job summary

Kezan Consulting in Gurugram is seeking a Python AI Engineer with 4+ years of experience to develop AI/GenAI applications using Python, FastAPI, and REST APIs.

You will work on LLM, RAG, Tool-calling, LangChain, OpenAI, and vector databases, building scalable solutions deployed on cloud platforms with Docker. Strong knowledge of SQL and CI/CD is essential.

Qualifications

• 4+ years of Python development experience.
• Hands-on with FastAPI/Flask and REST APIs.
• Strong understanding of LLMs, Generative AI, and RAG.
• Experience with LangChain / LangGraph.
• Experience with OpenAI or other LLM APIs.
• Knowledge of Vector Databases, Embeddings, and Semantic Search.
• Strong SQL and database fundamentals.
• Good understanding of Git, Docker, and CI/CD.
• Experience with AWS/Azure/GCP preferred.

Responsibilities

• Develop scalable AI/GenAI applications using Python, FastAPI, and REST APIs.
• Build and optimize LLM, RAG, and Agentic AI solutions.
• Work with LangChain, LangGraph, OpenAI APIs, and Hugging Face.
• Develop AI agents, tool-calling workflows, and multi-agent applications.
• Implement embeddings, vector search, and semantic search with Pinecone/FAISS.
• Design data ingestion, preprocessing, retrieval, and evaluation pipelines.
• Integrate AI solutions with databases, APIs, and enterprise apps.
• Deploy and maintain production AI apps using Docker and cloud platforms.
• Optimize performance, scalability, and reliability.

Skills

Python development

REST APIs

LLMs / Generative AI

LangChain / LangGraph

OpenAI APIs

Vector databases

SQL

Git / Docker / CI/CD

Cloud platforms (AWS/Azure/GCP)

Tools

Docker

FastAPI

Flask

CI/CD

AWS/Azure/GCP

Job description

Python AI Engineer 4+ Years

Location: Gurgaon/Gurugram
Experience: 4+ Years
Work Mode: Hybrid
Employment Type: Full-Time
Joining: Immediate

Job Overview

We are looking for a skilled Python AI Engineer with 4+ years of experience in Python development and hands-on experience in AI/ML, Generative AI, LLM, and RAG-based applications.

Key Responsibilities

• Develop scalable AI/GenAI applications using Python, FastAPI, and REST APIs.
• Build and optimize LLM, RAG, and Agentic AI solutions.
• Work with LangChain, LangGraph, OpenAI APIs, and Hugging Face.
• Develop AI agents, tool-calling workflows, and multi-agent applications.
• Implement embeddings, vector search, semantic search, and vector databases such as Pinecone/FAISS.
• Design data ingestion, preprocessing, retrieval, and evaluation pipelines.
• Integrate AI solutions with databases, APIs, and enterprise applications.
• Deploy and maintain production AI applications using Docker and cloud platforms.
• Optimize AI applications for performance, scalability, reliability, and response quality.

Must-Have Skills

• 4+ years of strong Python development experience.
• Hands-on experience with FastAPI/Flask and REST APIs.
• Strong understanding of LLMs, Generative AI, and RAG.
• Experience with LangChain / LangGraph.
• Experience with OpenAI or other LLM APIs.
• Knowledge of Vector Databases, Embeddings, and Semantic Search.
• Strong SQL and database fundamentals.
• Good understanding of Git, Docker, and CI/CD.
• Experience with AWS/Azure/GCP is preferred.

Good to Have

• Agentic AI / Multi-Agent Systems
• RAG evaluation using RAGAS / LangSmith
• MCP / Tool Calling / Function Calling
• PyTorch / TensorFlow / Scikit-learn
• Kubernetes and cloud deployment