LLM Integration Jobs

I am looking for someone who can take me from zero to a fully working Retrieval-Augmented Generation setup. The heart of the build is a robust vector database because the system must excel at high-dimensional data analysis: documents or embeddings come in, relevant context is pulled in milliseconds, and the language model produces grounded answers. Here is what I need the finished solution to do: data ingestion, embedding creation, storage inside the chosen vector store, fast similarity search, and seamless hand-off of results to the LLM for final generation. I am open on stack (Python-based pipelines, LangChain, FAISS, Milvus, Pinecone, or another tool you are comfortable with), as long as it remains well-documented and reproducible on a standard cloud VM or container. Deliverables 1....

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...

Project Title: Raspberry Pi Voice AI Prototype – Build Conversational Software for Plush AI Companion Project Description: I have a fully assembled hardware prototype for an AI companion plush toy (Raspberry Pi Zero 2 W + Adafruit Voice Bonnet + speaker + microphone setup + power system). The physical electronics are already built and ready. I need an experienced Raspberry Pi / Python developer to complete the software side only so the plush can have real-time voice conversations (must be in US). Scope of work: - Implement wake-word detection (Porcupine or similar) - Build a stable streaming voice pipeline: microphone input → STT → LLM (OpenAI / Grok / similar) → TTS → speaker output - Add half-duplex audio gating (mute mic while speaking to prevent feedback...