Role Overview:

We are seeking an experienced Agentic AI Engineer with strong expertise in Python and modern Generative AI frameworks. The ideal candidate will have hands-on experience designing, developing, and deploying enterprise-grade AI applications using LLMs, RAG architectures, and multi-agent systems. The candidate should be comfortable building intelligent autonomous workflows, integrating external tools, and deploying scalable AI solutions in cloud environments.

Key Responsibilities:

- Design, develop, and deploy Generative AI and Agentic AI solutions using Python.

- Build and optimize Retrieval-Augmented Generation (RAG) pipelines using vector databases and embedding models.

- Develop multi-agent workflows using LangGraph, including agent orchestration, state management, and memory handling.

- Create AI applications using LangChain and LangFlow for rapid development and workflow automation.

- Implement tool calling, function calling, API integrations, and external system interactions within AI agents.

- Design and implement MCP (Model Context Protocol) servers and integrations.

- Develop autonomous AI agents capable of reasoning, planning, task execution, and memory sharing.

- Deploy and monitor LLM-based applications in production environments.

- Integrate AI solutions with enterprise systems, APIs, databases, and cloud services.

- Collaborate with data scientists, software engineers, and business stakeholders to identify and implement AI use cases.

- Ensure scalability, performance, observability, and security of AI applications.

- Participate in architecture discussions, code reviews, and technical mentoring.

Mandatory Skills:

- Strong programming experience in Python.

- Hands-on experience with LangChain.

- Hands-on experience with LangGraph.

- Hands-on experience with LangFlow.

- Experience building and deploying LLM-based applications.

- Strong understanding of RAG (Retrieval-Augmented Generation) architecture.

- Experience building Agentic AI systems and autonomous agents.

- Hands-on experience with:

1. Multi-Agent Systems

2. Tool Calling / Function Calling

3. MCP (Model Context Protocol)

4. Agent Memory Management

5. Memory Sharing Across Agents

6. Workflow Orchestration

- Experience with vector databases such as Pinecone, ChromaDB, Weaviate, or FAISS.

- Experience integrating OpenAI, Claude, Gemini, Llama, Mistral, or similar models.

- Understanding of prompt engineering and LLM evaluation techniques.

Good to Have:

- Exposure to Machine Learning and Deep Learning concepts.

- Experience with model fine-tuning techniques such as LoRA, QLoRA, or PEFT.

- Knowledge of Hugging Face ecosystem.

- Experience with cloud platforms such as AWS, Azure, or GCP.

- Experience with Docker, Kubernetes, and CI/CD pipelines.

- Knowledge of MLOps practices and model monitoring.

- Experience with AI observability tools such as Langfuse, Arize, or Phoenix.