AI Engineer (Backend)

Tredence; Bengaluru; On-site; INR 2,600,000 - 3,800,000; Full time

Job summary

Tredence is hiring an AI Engineer (Backend) in Bengaluru to design and deploy AI-powered solutions using Generative AI, LLMs, and RAG. You will work on scalable Python backends, AI agent frameworks, and API-driven integrations.

The role emphasizes building production-grade pipelines, collaborating with product teams, and ensuring reliability and performance of AI systems at scale.

Qualifications

• 5–8 years of experience in AI engineering or backend development.
• Strong expertise in Generative AI and Python-based backend systems.
• Hands-on experience with LLMs, RAG, and autonomous AI agents.

Responsibilities

• Design and develop scalable AI applications using Python.
• Build GenAI solutions with OpenAI, Azure OpenAI, Claude, Gemini, or open-source models.
• Develop and maintain RAG pipelines integrating vector databases.
• Create AI agents using LangChain, LangGraph, CrewAI, AutoGen, or Semantic Kernel.
• Design REST APIs and microservices for AI model integration.
• Implement prompt engineering, grounding, evaluation, and optimization.
• Collaborate with product, data, and platform teams to deliver AI solutions.
• Monitor model performance and scalability in production.
• Participate in code reviews and enforce engineering best practices.

Skills

Generative AI

Python Development

Agentic AI Frameworks

Tools

LangChain

LangGraph

CrewAI

AutoGen

Semantic Kernel

FastAPI

REST APIs

Pinecone

Chroma

Weaviate

FAISS

Azure AI Search

Job description

AI Engineer (Backend)

Experience: 5 to 8 Years

Role Overview

We are seeking a highly skilled AI Engineer with strong expertise in Generative AI, Agentic AI, and Python-based backend development. The candidate will design, build, and deploy AI-powered applications leveraging Large Language Models (LLMs), Retrieval-Augmented Generation (RAG), and autonomous AI agent frameworks.

Key Responsibilities

• Design and develop scalable AI applications using Python.
• Build GenAI solutions leveraging OpenAI, Azure OpenAI, Claude, Gemini, or open-source LLMs.
• Develop and maintain RAG pipelines integrating vector databases and enterprise data sources.
• Create AI agents using frameworks such as LangChain, LangGraph, CrewAI, AutoGen, or Semantic Kernel.
• Design REST APIs and microservices for AI model integration.
• Implement prompt engineering, grounding, evaluation, and optimization techniques.
• Collaborate with product, data, and platform teams to deliver AI solutions.
• Monitor model performance, reliability, and scalability in production environments.
• Participate in code reviews and enforce engineering best practices.

Required Skills Primary Skills

• Generative AI
• Python Development
• Agentic AI Frameworks

Technical Skills

• LLMs and Foundation Models
• RAG Architecture
• LangChain / LangGraph
• CrewAI / AutoGen / Semantic Kernel
• FastAPI / Flask
• REST APIs
• Vector Databases (Pinecone, Chroma, Weaviate, FAISS, Azure AI Search)
• Prompt Engineering
• Git, CI/CD

Cloud & Infrastructure

• Azure (Preferred)
• AWS or GCP
• Docker
• Kubernetes (Good to Have)

Preferred Qualifications

• Experience working with enterprise AI use cases.
• Exposure to AI observability and evaluation frameworks.
• Understanding of responsible AI and AI governance principles.
• Experience in deploying AI applications in cloud environments.