
Gini Talent
Software Engineer – Azure AI Foundry
We are looking for talented Software Engineer to join our team and contribute to the design and development of cutting-edge AI-powered solutions. In this role, you will work hands-on with Azure AI Foundry and modern Generative AI technologies to build scalable, production-ready applications.
Key Responsibilities:
Design, develop, and deploy AI-driven applications using the Microsoft Azure ecosystem, with a strong focus on Azure AI Foundry
Build and optimize LLM-based solutions, including conversational agents, copilots, and intelligent workflows
Develop and maintain architectures leveraging RAG (Retrieval-Augmented Generation), embeddings, and vector databases
Work with modern agent frameworks such as LangGraph, AutoGen, LangChain, LlamaIndex, and Semantic Kernel to orchestrate complex AI workflows
Implement prompt engineering strategies and continuously improve model outputs through evaluation and iteration
Integrate AI solutions into existing systems using tool/function calling and structured outputs
Collaborate with cross-functional teams (product, data, design) to translate business requirements into scalable AI solutions
Ensure best practices in software development, including testing, CI/CD pipelines, and version control
Monitor, evaluate, and improve model performance, reliability, and cost-efficiency in production environments
Address security, compliance, and ethical considerations in AI system design
Required Qualifications:
Hands-on experience with Microsoft Azure, particularly Azure AI Foundry, for prototyping and production-level solutions
Strong experience with LLMs and GenAI technologies, including NLP fundamentals, prompt design, and model evaluation techniques
Proven experience with RAG architectures, embeddings, reranking strategies, and vector search implementations
Experience working with leading LLM providers such as Azure OpenAI, OpenAI, Anthropic, Google, Meta, and Mistral, as well as open-source models
Solid understanding of system design across data, model, and application layers, with the ability to evaluate trade-offs and risks
Proficiency in Python and strong software engineering fundamentals (clean code, testing, CI/CD, Git)
Experience with APIs, microservices architecture, and cloud-native application development
Familiarity with deploying and managing scalable applications in cloud environments
Nice to Have:
Experience with MLOps practices and tools
Knowledge of data engineering pipelines and big data technologies
Experience with monitoring, observability, and performance optimization in AI systems
Prior experience in building enterprise-grade AI products
View Other Positions