Job Type: Contract
Work Mode: Hybrid (3 Days from office)
Key Responsibilities
Design, develop, test, and deploy production-ready Agentic AI and GenAI services.
Build and maintain AI agent workflows using frameworks such as LangGraph, Pydantic AI, AG2, LangChain, or similar technologies.
Develop scalable APIs and microservices using FastAPI and related frameworks.
Implement containerized solutions using Docker and support deployment across cloud environments.
Collaborate with data scientists, product owners, and business stakeholders to translate requirements into robust AI solutions.
Establish engineering best practices, including code reviews, testing, CI/CD pipelines, and Git-based development workflows.
Monitor, troubleshoot, and optimize AI applications to ensure reliability, performance, and scalability.
Create clear technical documentation and maintain high-quality, maintainable code.
Required Qualifications:
5-10 years of software engineering, machine learning engineering, or AI engineering experience.
Strong proficiency in Python and modern software engineering principles.
Hands-on experience developing and deploying GenAI, Agentic AI, or LLM-powered applications.
Experience with agent orchestration frameworks such as LangGraph, Pydantic AI, AG2, AutoGen, CrewAI, or similar technologies.
Solid understanding of Retrieval-Augmented Generation (RAG), prompt engineering, tool calling, agent memory, and multi-agent architectures.
Experience building RESTful APIs using FastAPI or equivalent frameworks.
Strong experience with Docker, containerization, and cloud-native application development.
Familiarity with Azure services, including Azure OpenAI, Azure AI Foundry, Azure ML, Azure Functions, App Services, or similar platforms.
Experience implementing CI/CD pipelines and Git-based development workflows.
Strong debugging, problem-solving, and performance optimization skills.