AI Engineer

ITRadiant Solutions Inc.; Hyderabad; On-site; INR 1,500,000 - 2,700,000; Full time

Job summary

ITRadiant Solutions Inc. is seeking a hands-on AI/LLM Engineer to design, build, and deploy AI-powered applications such as chatbots, knowledge assistants, and document AI in production. You will integrate with major LLM providers and develop RAG pipelines and AI agents.

You will also build scalable Python backends with FastAPI, deploy on Azure/AWS, and work with vector databases for semantic search. Strong cloud experience and CI/CD proficiency are required.

Qualifications

• 2–4 years hands-on experience building and shipping AI/LLM solutions in production.
• Strong Python expertise with FastAPI, async programming, and REST API development.
• Hands-on experience with at least two LLM providers Azure OpenAI, OpenAI, Anthropic Claude, Gemini, or Amazon Bedrock.
• Practical knowledge of RAG, prompt engineering, function calling, structured outputs, and AI agents.
• Experience with LLM frameworks LangChain, LangGraph, LlamaIndex, Semantic Kernel, CrewAI, or AutoGen.
• Proficiency in vector databases such as Azure AI Search, pgvector, Pinecone, Qdrant, or Weaviate.
• AWS experience: Bedrock, ECS/EKS, Lambda, S3, RDS, API Gateway, CloudWatch, IAM.
• Hands-on with Docker, Kubernetes, and CI/CD pipelines.
• Must have independently built at least 3 of the following: AI Chatbot, Knowledge Assistant, Document AI/OCR, Email Automation, Ticket Classification, AI Copilot, AI Search, Workflow Automation, AI Agent, or Multi-Agent System.

Responsibilities

• Design, build, and deploy AI/LLM-powered applications including chatbots, knowledge assistants, document AI, and multi-agent systems.
• Integrate with LLM providers such as Azure OpenAI, OpenAI, Anthropic Claude, Google Gemini, and Amazon Bedrock.
• Develop RAG pipelines, AI agents, and agentic workflows using LangChain, LangGraph, LlamaIndex, or similar frameworks.
• Build scalable Python backends using FastAPI with async programming and REST API design.
• Deploy and manage applications on Azure and AWS cloud infrastructure.
• Work with vector databases and implement semantic search and retrieval solutions.
• Set up and maintain CI/CD pipelines using GitHub Actions or Azure DevOps.
• Collaborate with cross-functional teams to translate business requirements into AI solutions.

Skills

Python

FastAPI

Async programming

REST API development

LLM providers

Prompt engineering

AI agents

RAG pipelines

CI/CD

Tools

Docker

Kubernetes

GitHub Actions

Azure DevOps

Azure OpenAI

OpenAI

LangChain

LangGraph

LlamaIndex

Pinecone

Qdrant

Weaviate

AWS Bedrock

Job description

• Design, build, and deploy AI/LLM-powered applications including chatbots, knowledge assistants, document AI, and multi-agent systems
• Integrate with LLM providers such as Azure OpenAI, OpenAI, Anthropic Claude, Google Gemini, and Amazon Bedrock
• Develop RAG pipelines, AI agents, and agentic workflows using LangChain, LangGraph, LlamaIndex, or similar frameworks
• Build scalable Python backends using FastAPI with async programming and REST API design
• Deploy and manage applications on Azure and AWS cloud infrastructure
• Work with vector databases and implement semantic search and retrieval solutions
• Set up and maintain CI/CD pipelines using GitHub Actions or Azure DevOps
• Collaborate with cross-functional teams to translate business requirements into AI solutions

Required Skills:

• 2-4 years of hands-on experience building and shipping AI/LLM solutions in production
• Strong Python expertise with FastAPI, async programming, and REST API development
• Hands-on experience with at least two LLM providers Azure OpenAI, OpenAI, Anthropic Claude, Gemini, or Amazon Bedrock
• Practical knowledge of RAG, prompt engineering, function calling, structured outputs, and AI agents
• Experience with LLM frameworks LangChain, LangGraph, LlamaIndex, Semantic Kernel, CrewAI, or AutoGen
• Proficiency in vector databases such as Azure AI Search, pgvector, Pinecone, Qdrant, or Weaviate
• AWS experience: Bedrock, ECS/EKS, Lambda, S3, RDS, API Gateway, CloudWatch, IAM
• Hands-on with Docker, Kubernetes, and CI/CD pipelines
• Must have independently built at least 3 of the following: AI Chatbot, Knowledge Assistant, Document AI/OCR, Email Automation, Ticket Classification, AI Copilot, AI Search, Workflow Automation, AI Agent, or Multi-Agent System

Good to Have:

• Microsoft Copilot Studio or Power Platform
• Hugging Face, Ollama, or NVIDIA NIM
• MLflow, LangSmith, or Langfuse for AI observability
• Knowledge of AI security and governance practices
• Terraform for infrastructure as code