Back
Mid-level, generalist fullstack title plus 3–6yr range and broad skillset makes competition high.
Specialized LLM/GenAI skillset makes cross-industry transferability low, so background fit sensitivity is high.
Explicit 3–6yr requirement and many mandatory LLM/backend techs imply high shortlisting strictness.
Login to See Your Match Score
Create a free account or log in to unlock your CV match score across:
Design, develop, and deploy scalable backend APIs and multi-agent AI systems for Generative AI applications on Azure Cloud.
Implement Retrieval-Augmented Generation (RAG) pipelines, MCP-compliant tool servers, and secure agent-to-agent communication using advanced AI orchestration techniques.
Optimize AI systems for latency, scalability, cost, and reliability including monitoring, observability, and evaluation frameworks.
3 to 6 years of backend software development experience.
2 to 3 years of hands-on experience building LLM/GenAI applications.
Strong proficiency in Python with async programming, FastAPI for RESTful APIs and WebSocket, and solid OOP/system design principles.
Experience with Generative AI frameworks (LangChain, LangGraph), MCP and A2A protocols, cloud deployment on AWS/Azure, and database technologies like PostgreSQL or MongoDB.
Experienced in end-to-end GenAI system architecture including multi-agent orchestration and RAG implementations suitable for production environments.
Skilled in integrating complex backend AI services with responsive frontend applications and deploying these on cloud platforms with performance tuning.
Practically familiar with agent communication protocols, secure AI workflows, and implementing AI evaluation and guardrail frameworks to ensure system reliability.