Found Description
Overview
Build and scale a pro‑code autonomous agent ecosystem using modern open‑source AI technologies across agent orchestration, LLMOps, AI safety, inference, Kubernetes, and full‑stack user interfaces.
Key Responsibilities
- Design and build complex stateful multi‑agent systems using LangGraph, CrewAI, or AutoGen.
- Develop advanced agentic RAG pipelines using LlamaIndex, Haystack, or similar frameworks.
- Implement custom tool‑calling logic and Model Context Protocol integrations, connecting AI agents with internal databases, APIs, and enterprise systems.
- Architect a robust AI safety layer using Guardrails AI, NVIDIA NeMo Guardrails, or Meta Llama Guard, alongside real‑time monitoring and observability for LLM inputs and outputs.
- Deploy and optimise open‑source models such as Llama, Mistral, or Qwen using high‑performance inference tools like vLLM, Hugging Face TGI, Ollama, or Seldon Core.
- Build scalable AI...