About the role
We are looking for an experienced AI Engineer with a strong background in Agentic AI development, Generative AI, and Large Language Model (LLM) orchestration. The ideal candidate will design, build, and optimize intelligent autonomous systems and agent workflows for enterprise-grade applications.
Responsibilities:
- Develop and deploy agentic AI systems with task planning, tool orchestration, and context management.
- Design and implement multi-agent workflows using frameworks such as LangGraph, LangChain, Autogen, CrewAI, or Agentic Workbench.
- Build RAG (Retrieval-Augmented Generation) pipelines with embeddings, vector stores, and semantic search optimization.
- Optimize LLM performancereasoning accuracy, hallucination control, and grounding score evaluation.
- Implement system prompts, role prompts, and tool/function calling strategies.
- Integrate AI agents with external enterprise platforms (ServiceNow, SAP, Workday, etc. ).
- Collaborate with cross-functional teams to translate real-world workflows into intelligent AI-powered automation.
- Contribute to internal AI orchestration frameworks and reusable components.
Requirements:
- 4-10 years of software engineering experience.
- Strong hands-on experience in Agentic AI Development (not just API calling).
- Proficiency in Python or Node.js .
- Expertise in LLM orchestration, prompt engineering, context window management, and reasoning optimization.
- Experience with RAG pipelines, vector databases (Pinecone, Chroma, FAISS, MongoDB, ClickHouse, etc. ).
- Understanding of cloud-native environments (AWS, GCP, or Azure) and distributed systems.