Back to jobs
Featured role

AI/ML Engineer – Agentic AI

Maple Learning Solutions
On-site
Full-time
Posted 16/10/2026
Expires 15/11/2026

Ready to apply?

Sign in through LXD Guild to unlock ATS-backed profile support, resume matching, and the guided application flow.

Related L&D opportunities

Job description

AI/ML ENGINEER – AGENTIC AI LOCATION: Hyderabad, Telangana, India EMPLOYMENT TYPE: Full-Time EXPERIENCE: 4–5+ Years ABOUT THE ROLE We are looking for an experienced AI/ML Engineer – Agentic AI to design, develop, and deploy production-ready AI agents capable of reasoning, planning, tool usage, decision-making, and multi-step task execution. The role involves building LLM-powered applications, developing autonomous workflows, implementing Retrieval-Augmented Generation (RAG), integrating AI agents with enterprise systems, and ensuring the reliability, security, and scalability of AI solutions. The ideal candidate should have strong Python development skills, hands-on experience with Large Language Models (LLMs) and agent frameworks, and the ability to take AI solutions from development to production.

KEY RESPONSIBILITIES

1. AGENTIC AI DEVELOPMENT

  • Design, develop, and deploy agentic AI systems and LLM-powered applications.
  • Build AI agents capable of reasoning, planning, decision-making, and multi-step task execution.
  • Develop autonomous workflows that use tools and external systems to complete tasks.
  • Implement agent orchestration and collaboration between AI agents where required.
  • Optimize agent performance, reliability, and execution efficiency.

2. LLM APPLICATIONS & AGENT FRAMEWORKS

  • Develop AI agents using LangGraph, LangChain, AutoGen, CrewAI, Semantic Kernel, or similar frameworks.
  • Implement tool calling, function calling, structured outputs, and agent state management.
  • Design workflows that enable agents to interact with APIs, databases, and external tools.
  • Integrate LLM capabilities into production-ready applications.
  • Evaluate and select suitable frameworks and models based on project requirements.

3. RAG, VECTOR SEARCH & MEMORY

  • Design and implement Retrieval-Augmented Generation (RAG) pipelines.
  • Integrate vector databases and semantic search capabilities into AI applications.
  • Develop context retrieval, conversation memory, and knowledge-grounding mechanisms.
  • Improve retrieval accuracy, response relevance, and contextual