Role & responsibilities

Build and productionize AI capabilities LLM applications, RAG systems and agentic AI workflows. This is a hands-on engineering role, not research or prompt engineering alone.
- Build LLM-powered enterprise applications and AI/ML components
- Develop RAG pipelines: document ingestion, chunking, embedding, retrieval
- Build agentic workflows, tool-using agents and multi-step orchestration
- Implement tool/function calling with controlled, permission-aware execution
- Integrate models and agents with enterprise APIs, applications and data platforms
- Build evaluation frameworks retrieval quality, groundedness, task completion
- Implement guardrails, human-in-the-loop controls, logging, tracing and observability

Preferred candidate profile

2–5+ years in software, ML or AI engineering,



with production AI/ML or agentic applications actually shipped.
- Strong Python and software engineering fundamentals
- Solid grasp of LLM application architecture, RAG patterns, embeddings and vector search
- Experience designing AI evaluation and working with model/agent observability
- Able to debug AI systems beyond prompt changes
- Understanding of AI security, guardrails and safe tool access
- Exposure to LangChain, LangGraph, LlamaIndex, Hugging Face, PyTorch, MLflow, and vector DBs such as Milvus, Pinecone, Weaviate or pgvector
- Enterprise implementation experience preferred

Robust applied AI experience can offset fewer total years.

📌 Artificial Intelligence Engineer (Sahibzada Ajit Singh Nagar)
🏢 XenonStack
📍 Sahibzada Ajit Singh Nagar