Role & Responsibilities -

- Design, develop, and deploy enterprise-grade Generative AI and Agentic AI applications using Python, Azure OpenAI, and relevant AI frameworks.
- Build sophisticated Agentic AI workflows and multi-agent architectures involving supervisor agents, planner agents, utility agents, and specialized task-execution agents.
- Develop agent orchestration workflows for autonomous decision-making, task planning, tool selection, API execution, validation, and multi-step problem-solving.
- Implement tool calling, function calling, and REST API integrations to connect AI agents with enterprise applications, databases, and business systems.
- Build and optimize LLM-powered applications using LangChain, LangGraph, or equivalent agent orchestration frameworks.
- Develop Retrieval-Augmented Generation (RAG) pipelines using embeddings, vector databases, semantic search, and enterprise knowledge sources to provide contextually relevant and grounded responses.
- Implement agent state management, workflow routing, error handling, retries, fallback mechanisms, and human-in-the-loop controls for reliable AI execution.
- Integrate Azure OpenAI and Azure AI services into scalable enterprise AI solutions.
- Develop backend services and AI APIs using Python, FastAPI, and REST APIs.
- Implement LLM evaluation, response validation, hallucination mitigation, and performance optimization to improve the reliability of AI-generated outputs.
- Monitor and optimize AI application performance, latency, token consumption, retrieval quality, and execution accuracy.
- Collaborate with business stakeholders, architects, and engineering teams to translate complex business requirements into scalable Agentic AI solutions.
- Follow engineering best practices for security, access control, testing, deployment, maintainability, and production readiness.





Preferred Candidate Profile

- Strong hands-on experience in Generative AI, Agentic AI, and AI application development, with demonstrable experience building agentic workflows in real-world projects.
- Strong Python programming and backend development experience.
- Proven experience designing and implementing multi-agent systems and agent orchestration workflows. Candidates with only basic chatbot or standalone RAG experience will not be sufficient.
- Hands-on experience with LangGraph, LangChain, AutoGen, CrewAI, Semantic Kernel, or equivalent frameworks.
- Strong understanding of agent planning, routing, tool selection, function calling, API execution, workflow state management, and agent collaboration.
- Experience integrating LLMs with enterprise APIs, databases, and external tools.
- Hands-on experience with Azure OpenAI and preferably Azure AI services.
- Valuable understanding of RAG, embeddings, vector databases, semantic search, and prompt engineering.
- Experience handling agent failures, retries, validation, guardrails, and human approval workflows.
- Understanding of LLM evaluation, hallucination reduction, tracing, monitoring, and performance optimization.
- Experience developing production-ready AI applications using FastAPI, REST APIs, and scalable backend architectures.
- Strong problem-solving, debugging, communication, and stakeholder collaboration skills.
- Ability to explain the architecture, workflow design, tools, integrations, and code personally implemented in previous Agentic AI projects.

Key Must-Haves: Agentic AI, multi-agent workflow implementation, Python, LLM/GenAI, agent orchestration, tool/function calling, and hands-on experience with LangGraph or an equivalent framework.

Good to Have: Azure OpenAI, Azure AI Search, MCP (Model Context Protocol), advanced RAG, LLM observability, evaluation frameworks, Docker, Kubernetes, and CI/CD.

📌 Artificial Intelligence Engineer (Hyderabad)
🏢 Allegis Group
📍 Hyderabad