Python and AI Engineer

Role Overview

This position involves designing, developing, and optimizing advanced AI applications leveraging Python and large language model frameworks. The engineer will be responsible for creating robust Retrieval-Augmented Generation (RAG) pipelines and implementing complex multi-agent orchestration workflows. The role also requires managing vector databases, developing APIs, and refining prompt mechanisms to enhance response quality while ensuring system scalability and reliability.

Key Responsibilities

• Create AI-driven solutions utilizing Python and LLM technology.
• Construct and enhance RAG pipeline architectures.
• Design workflows for coordinating multiple AI agents effectively.
• Work extensively with vector databases such as FAISS, Pinecone, and Weaviate.
• Develop API endpoints using frameworks like FastAPI or Flask.
• Implement prompt engineering strategies to optimize AI responses.
• Guarantee the performance, scalability, and reliability of AI applications.

Required Skills and Experience

• Minimum of six years' experience in backend development with Python.
• At least one year of practical experience in Agentic AI development.
• Proficient knowledge of Python programming essentials.
• Hands-on experience with LangChain or LangGraph frameworks.
• In-depth understanding of Retrieval-Augmented Generation (RAG) principles.
• Practical exposure to agent frameworks such as LangGraph, CrewAI, or AutoGen.
• Familiar with large language models including GPT, Claude, and Mistral.
• Experienced with vector search technologies and embedding techniques.

Eligibility Criteria

Applicants must hold at least a graduate degree in any discipline.

Compensation

The offered salary ranges from 1,500,000 INR to 3,000,000 INR annually.