AI Engineer

Codians; Mumbai; On-site; INR 1,400,000 - 2,200,000; Full time

Job summary

Codians in Mumbai is seeking Applied AI Engineers with hands-on experience in building end-to-end AI applications and deploying intelligent AI systems using modern LLM-based architectures.

You will own the full RAG pipeline, design agent-based workflows, and optimize retrieval with guardrails for production-grade AI solutions. Proficiency in Python, LangChain/LangGraph, and vector databases is required.

Qualifications

• 3+ years of hands-on experience in AI/ML, Backend Engineering, or Applied AI development.

Responsibilities

• Design and build end-to-end AI applications, including RAG systems, agentic workflows, chatbots, and internal AI tools.
• Own the complete RAG pipeline: ingestion, chunking, indexing, retrieval and generation.
• Implement agent-based systems with tool calling, memory handling, and multi-step reasoning.
• Optimize retrieval mechanisms, tuning, and reranking strategies to ensure reliability.
• Ensure production-ready AI systems with evaluation frameworks, guardrails, latency and cost optimization.
• Implement fallback mechanisms to maintain service reliability when models fail.
• Develop model routing and control strategies using Model Control / Management Plans (MCPs).
• Deliver AI solutions that convert data into reasoning and actionable outcomes.

Skills

AI/ML

Backend Engineering

RAG systems

Python

LangChain

LangGraph

Vector databases

LLM APIs

Cloud exposure (GCP)

Tools

LangChain

LangGraph

Vector Databases

Job description

Role Overview

We are looking for Applied AI Engineers who have hands-on experience building end-to-end AI applications, not just ML pipelines or infrastructure. The ideal candidate should be capable of designing and deploying intelligent AI systems that solve real business problems using modern LLM-based architectures.

Key Responsibilities

• Design and build end-to-end AI applications such as RAG systems, agentic workflows, chatbots, and internal AI tools.
• Own the complete RAG pipeline, including data ingestion, chunking, indexing, retrieval, and generation.
• Implement agent-based systems with tool calling, memory handling, and multistep reasoning.
• Optimize retrieval mechanisms and handle retrieval failures, tuning, and reranking strategies.
• Ensure production-ready AI systems with evaluation frameworks, guardrails, and latency/cost optimization.
• Implement fallback mechanisms to maintain service reliability when models fail.
• Develop model routing and control strategies using Model Control / Management Plans (MCPs).
• Deliver AI solutions that convert data → reasoning → actionable outcomes.

Requirements

• 3+ years of experience in AI/ML, Backend Engineering, or Applied AI development.
• Proven experience building end-to-end AI applications, not just ML pipelines.
• Strong understanding of Retrieval-Augmented Generation (RAG) systems.
• Hands-on experience managing the full RAG pipeline (ingestion → chunking →indexing → retrieval → generation).
• Deep understanding of retrieval internals including: o Chunking strategys o Embeddings o Indexing and re-ranking o Retrieval tuning and failure handling1.
• Experience working with agentic frameworks including tool calling, memory, and multi-step reasoning.
• Strong understanding of Managed AI Services, fallback mechanisms, and service reliability.
• Knowledge of Model Control / Management Plans (MCPs) and model routing strategies.
• Experience deploying production-ready AI systems with focus on evaluation, guardrails, latency, and cost trade-offs.
• Proficiency in Python.
• Experience with LangChain or LangGraph.
• Experience working with Vector Databases.
• Experience integrating LLM APIs.
• Exposure to GCP tools or cloud-based AI services is a plus