Senior Agentic AI Engineer – Python (6+ Years Experience | Remote | Immediate Joiners)

YMinds.AI; Bengaluru; On-site; INR 350,000 - 700,000; Full time

Job summary

YMinds.AI is seeking a Senior Agentic AI Engineer with strong Python expertise to build and deploy production-grade Agentic AI and Generative AI solutions.

The ideal candidate should have hands-on experience with Python, AI Agents, RAG, LLMs, LangGraph/LangChain, APIs, and vector databases, with the ability to design scalable and reliable AI applications.

Qualifications

• 6+ years of Python backend experience with REST APIs/microservices.
• Hands-on with Agentic AI, AI Agents, tool calling, planning, reasoning, orchestration, and memory/state management.

Responsibilities

• Build and deploy Agentic AI and Generative AI applications.
• Develop scalable Python APIs, backend services, and microservices.
• Build AI agents with tool calling, function calling, planning, reasoning, memory, and multi-step workflows.
• Design and implement RAG pipelines and retrieval workflows.
• Develop stateful workflows using LangGraph / LangChain.
• Integrate agents with APIs, databases, vector stores, enterprise systems, and external tools.
• Work with OpenAI, Azure OpenAI, Claude, Gemini, AWS Bedrock, and open-source LLMs.
• Deploy and optimize AI applications on AWS, Azure, or GCP.
• Implement evaluation, monitoring, observability, guardrails, and production best practices.
• Optimize applications for performance, latency, reliability, scalability, and cost.

Skills

Python

Agentic AI

AI Agents

RAG

LangChain

LangGraph

APIs

Vector DBs

LLMs

Cloud deployment

Tools

LangChain

LangGraph

Pinecone

FAISS

Job description

Our client is seeking a Senior Agentic AI Engineer with strong Python expertise to build and deploy production-grade Agentic AI and Generative AI solutions.

The ideal candidate should have strong hands‑on experience with Python, AI Agents, RAG, LLMs, LangGraph/LangChain, APIs, and vector databases, with the ability to design scalable and reliable AI applications.

Key Responsibilities

• Build and deploy Agentic AI and Generative AI applications
• Develop scalable Python APIs, backend services, and microservices
• Build AI agents with tool calling, function calling, planning, reasoning, memory, and multi-step workflows
• Design and implement RAG pipelines and retrieval workflows
• Develop stateful workflows using LangGraph / LangChain
• Integrate agents with APIs, databases, vector stores, enterprise systems, and external tools
• Work with OpenAI, Azure OpenAI, Claude, Gemini, AWS Bedrock, and open-source LLMs
• Deploy and optimize AI applications on AWS, Azure, or GCP
• Implement evaluation, monitoring, observability, guardrails, and production best practices
• Optimize applications for performance, latency, reliability, scalability, and cost

Required Skills

• 6+ years of strong Python experience, including backend development, REST APIs, microservices, FastAPI, and/or Flask
• Strong production experience with Agentic AI, AI Agents, tool calling, planning, reasoning, orchestration, memory/state management, and human-in-the-loop workflows
• Strong experience with RAG, including ingestion, chunking, embeddings, semantic/vector search, hybrid retrieval, reranking, and hallucination reduction
• Experience with OpenAI/GPT, Azure OpenAI, Claude, Gemini, AWS Bedrock, or open-source LLMs
• Hands‑on experience with LangGraph and/or LangChain
• Experience with vector databases such as Pinecone, FAISS, ChromaDB, Weaviate, Qdrant, Milvus, pgvector, Azure AI Search, or OpenSearch
• Strong understanding of Prompt Engineering, Context Engineering, structured outputs, function calling, and guardrails
• Strong knowledge of REST APIs, SQL/NoSQL, Git, Docker, CI/CD, monitoring, logging, and API security
• Experience with AWS, Azure, or GCP
• Experience with LLMOps/MLOps and production AI deployments

Nice to Have

• Multi-agent systems
• Agentic RAG / Advanced RAG
• Graph RAG / Knowledge Graphs
• AutoGen, CrewAI, or LlamaIndex
• LLM evaluation and observability
• AI guardrails and prompt‑injection mitigation

Keywords