LLM integráció Jobs

Description We are building a network of specialists who help validate and improve the reliability of enterprise AI systems. Our company, , works with organisations deploying AI assistants and knowledge systems powered by large language models and RAG (Retrieval-Augmented Generation). Your role will be to review AI responses, detect hallucinations, validate grounding against source material, and help create evaluation datasets. This is not model development. This role focuses on AI quality assurance and validation. Responsibilities • Review LLM responses for factual accuracy • Identify hallucinations and fabricated references • Verify whether answers are grounded in provided documents • Detect retrieval vs generation failures in RAG systems • Score responses...

ROLE SUMMARY We are seeking a hands-on AI Systems Engineer with strong DevOps and LLM integration experience to design, deploy, and optimise a self-hosted AI agent (OpenClaw) running on a VPS. This is not a basic chatbot project. The role involves building a persistent, autonomous AI system that integrates: • LLMs (OpenAI, Claude, etc.) • Messaging platforms (Telegram) • Web-based dashboards • Task execution workflows CORE COMPETENCIES REQUIRED 1. DevOps & Infrastructure (Non-negotiable) The candidate must have real production deployment experience: • Linux server management (Ubuntu preferred) • VPS provisioning (Hetzner, AWS, DigitalOcean, etc.) • Containerisation: • Docker • Docker Compose • Reverse proxy setup: &bu...