Gen AI Developer

Brace Infotech; Hyderabad; Hybrid; INR 1,500,000 - 2,100,000; Full time

Job summary

Brace Infotech in Hyderabad is seeking a senior software engineer to lead GenAI initiatives. You will design and deliver scalable AI-powered applications, integrating Azure AI Foundry, OpenAI models, and enterprise data sources.

You will prototype RAG pipelines, implement prompt engineering practices, and collaborate with product teams to deploy secure, cost-aware GenAI solutions across systems and databases.

Qualifications

• 5+ years of software development experience with Python.
• Hands-on experience with Generative AI and LLM based applications.
• Proven experience with Azure Foundry and Azure OpenAI.
• Experience building RAG-based applications with Azure AI Search and embeddings.
• Experience developing and integrating AI Agents / Agentic AI solutions.
• Strong understanding of LangChain, Semantic Kernel, or LlamaIndex.
• Experience integrating GenAI with REST APIs and enterprise systems.
• Strong SQL, data processing, Git, CI/CD, and cloud deployment.
• Knowledge of AI security, prompt injection, and guardrails.

Responsibilities

• Develop GenAI solutions using Azure Foundry and Azure OpenAI.
• Build and optimize RAG pipelines with vector search and embeddings.
• Create scalable, secure AI applications integrated with enterprise data.
• Collaborate with product teams to deploy monitoring and cost controls.

Skills

Python

Azure AI Foundry

Generative AI

Azure OpenAI

Prompt Engineering

RAG

Azure AI Search

Embeddings

AI Agents

GenAI Frameworks

REST APIs

SQL

Git

CI/CD

Docker

AI Security

LLM Evaluation

Token Cost Monitoring

Tools

Docker

Git

CI/CD

Job description

Role & responsibilities

Technical Skills Mandatory

• 5+ years of software development experience with strong Python skills.
• Hands-on experience with Azure AI Foundry / Microsoft Foundry.
• Strong experience developing Generative AI and LLM-based applications.
• Hands-on experience with Azure OpenAI / Azure-hosted foundation models.
• Strong knowledge of Prompt Engineering and prompt optimization.
• Experience implementing RAG (Retrieval-Augmented Generation) solutions.
• Experience with Azure AI Search / vector search / semantic search.
• Experience with embeddings and vector databases.
• Hands-on experience developing AI Agents / Agentic AI solutions.
• Experience with frameworks such as LangChain, Semantic Kernel, or LlamaIndex.
• Experience integrating AI solutions with REST APIs, enterprise applications, databases, and document repositories.
• Strong SQL and data processing skills.
• Experience with Git, CI/CD, Docker, and cloud deployment.
• Understanding of LLM evaluation, hallucination reduction, guardrails, and responsible AI.
• Understanding of AI security, including prompt injection, data leakage prevention, authentication, authorization, and secure API integration.
• Experience with application monitoring, logging, performance optimization, and LLM/token cost monitoring.

Technical Skills (Must Have)

• 5+ years of software development experience with strong hands-on expertise in Python.
• Strong hands-on experience in Generative AI and LLM application development.
• Proven experience with Azure AI Foundry / Microsoft Foundry and Azure OpenAI.
• Strong hands-on experience building RAG-based applications using Azure AI Search, embeddings, vector search, and vector databases.
• Experience developing and integrating AI Agents / Agentic AI solutions.
• Strong understanding of Prompt Engineering, LLM evaluation, response optimization, and AI guardrails.
• Experience with LangChain, Semantic Kernel, LlamaIndex, or equivalent GenAI frameworks.
• Experience integrating GenAI applications with REST APIs, enterprise applications, databases, and document/knowledge repositories.
• Strong knowledge of SQL, data processing, Git, CI/CD, and cloud deployment.
• Understanding of AI security and Responsible AI, including prompt injection, data protection, authentication, authorization, and secure API integration.
• Experience with production deployment, application monitoring, logging, performance optimization, and LLM/token cost management.
• Ability to develop scalable, secure, reliable, and production-ready GenAI solutions.