AI Solutions Engineer

Jobtailor; Bengaluru; On-site; INR 1,500,000 - 2,300,000; Full time

Job summary

Jobtailor in Bengaluru seeks an AI Engineer to design and deploy RAG systems for document processing, policy analysis, and compliance automation. You will build AI apps using Azure OpenAI, Azure AI Foundry, and Azure Cognitive Services, and develop multi‑agent solutions with AutoGen and Semantic Kernel.

You will create production‑grade REST APIs with FastAPI, apply prompt engineering, and integrate AI with enterprise data sources.

Qualifications

• 2+ years hands-on experience with Azure OpenAI and related services.
• Strong Python production coding experience.
• Experience building RAG systems with vector databases.
• Familiarity with LLM APIs and tuning parameters (temperature, top-p, frequency penalty).
• Experience with at least one API framework (FastAPI, Flask, or Django).
• Understanding embeddings, chunking strategies, and retrieval optimization.
• Familiarity with prompt engineering techniques (few-shot, chain-of-thought, structured outputs).
• Experience with async programming in Python.
• Basic understanding of Azure cloud services.
• Ability to debug and troubleshoot AI systems in production.

Responsibilities

• Design and implement RAG systems for document processing and compliance.
• Build AI apps using Azure OpenAI and Azure AI Foundry.
• Develop multi-agent systems using AutoGen, Semantic Kernel, or LangGraph.
• Create production-grade REST APIs using Python (FastAPI).
• Implement prompt engineering strategies including few-shot learning and structured outputs.
• Integrate AI solutions with enterprise data sources (databases, document repositories, external APIs).
• Optimize LLM performance including context window management and token optimization.
• Handle LLM security including prompt injection prevention and guardrails.
• Deploy and maintain AI infrastructure using Azure services and CI/CD pipelines.
• Troubleshoot and resolve production issues in AI systems.
• Collaborate with front-end teams (Next.js) to deliver complete solutions.
• Collaborate with product managers and business analysts to translate customer needs into AI requirements.
• Contribute to building reusable frameworks and integration components for rapid AI deployment.
• Participate in code reviews, sprint planning, and Agile ceremonies.
• Assist in preparing technical documentation, deployment guides, and maintenance procedures.
• Work closely with senior engineers to integrate AI models into production applications.
• Stay current with Microsoft’s evolving AI ecosystem to identify opportunities for improvement.
• Propose enhancements to existing AI solutions through improved orchestration or model optimization.
• Participate in internal knowledge sessions to deepen expertise in LLM integration and AI governance.
• Support experimentation with complex multi-agent coordination using AutoGen and Semantic Kernel.

Skills

Python programming

Async programming

LLM integration

Prompt engineering

Tools

Azure OpenAI

Azure AI Foundry

Azure Cognitive Services

FastAPI

Pinecone

Weaviate

AutoGen

Semantic Kernel

Job description

Responsibilities

• Design and implement RAG systems for document processing, policy analysis, and compliance automation.
• Build and deploy AI applications using Azure OpenAI, Azure AI Foundry, and Azure Cognitive Services.
• Develop multi-agent systems using frameworks like AutoGen, Semantic Kernel, or LangGraph.
• Create production-grade REST APIs using Python (FastAPI) for AI services.
• Implement prompt engineering strategies including few-shot learning, chain-of-thought, and structured output generation.
• Integrate AI solutions with enterprise data sources (databases, document repositories, external APIs).
• Optimize LLM performance including context window management, token optimization, and response quality.
• Handle LLM security including prompt injection prevention, guardrails, and content filtering.
• Deploy and maintain AI infrastructure using Azure services and CI/CD pipelines (Bicep, Azure DevOps).
• Troubleshoot and resolve production issues in AI systems.
• Collaborate with front-end teams (Next.js) to deliver complete solutions.
• Collaborate with product managers and business analysts to translate customer needs into actionable AI requirements.
• Contribute to building reusable frameworks, orchestration templates, and integration components for rapid AI solution deployment.
• Participate in code reviews, sprint planning, and Agile ceremonies to ensure consistent quality and high-velocity delivery.
• Assist in preparing technical documentation, deployment guides, and maintenance procedures.
• Work closely with senior engineers to integrate AI models into production applications, ensuring performance, reliability, and scalability.
• Stay current with Microsoft’s evolving AI ecosystem to identify opportunities for improvement and innovation.
• Propose enhancements to existing AI solutions through improved orchestration, automation, or model optimization.
• Participate in internal knowledge sessions to deepen expertise in LLM integration, prompt engineering, RAG implementations, and AI governance.
• Support experimentation with complex multi-agent coordination using AutoGen and Semantic Kernel.

Requirements

• 2+ years of hands‑on experience using Azure OpenAI, Azure AI Foundry, and Azure Cognitive Services.
• Strong Python programming skills with production code experience.
• Experience building RAG systems with vector databases (Azure AI Search, Pinecone, Weaviate, or similar).
• Working knowledge of LLM APIs (Azure OpenAI, OpenAI) including parameters like temperature, top‑p, frequency penalty.
• Experience with at least one API framework (FastAPI, Flask, or Django).
• Understanding of embeddings, chunking strategies, and retrieval optimization.
• Familiarity with prompt engineering techniques (few-shot, chain‑of‑thought, structured outputs).
• Experience with async programming in Python.
• Basic understanding of Azure cloud services.
• Ability to debug and troubleshoot AI systems in production.