Python AI Engineer for LLM Deployment

We're not just another AI shop – we're a people-first business on a mission to solve real-world problems, from removing CO₂ from the atmosphere to building tools that actually matter. And we want you to grow with us – not for 7 days, but for years. This gig starts as a part‑time 7‑10 day project, but if you're the right fit, we're keeping you long‑term. We need a Python AI Engineer who wants to build something epic, have fun, and be part of a team that actually cares. Still with us? Good. Here's what we're building: --- PYTHON AI ENGINEER – PART-TIME (7–10 DAY PROJECT) Long-term role for the right person. We are deploying a full AI ecosystem with LLMs, memory systems, search, video generation, and creative tools. We need a Python AI Engineer to deploy the AI core on production infrastructure. This is a PRODUCTION deployment role – NOT research. --- WHAT YOU'LL DO: · Deploy vLLM inference servers on RunPod GPU pods (Llama 3.3 70B, Qwen 2.5 Coder 32B, DeepSeek R1 32B, BGE-large) · Set up OpenAI-compatible API endpoints, VRAM management, Flash Attention, health checks · Build Memory Service (FastAPI) – embeddings with BGE, vector storage with Qdrant, similarity search · Build Brain Gateway (FastAPI) – router for LLM requests, orchestration, context retrieval, session management · Build Scraping Worker – web scraping, text chunking, async processing with NATS · Set up RAG pipeline with Qdrant + Typesense (hybrid search) · Deploy FLUX / Playground inference + Whisper.cpp for subtitles + Video Engine API · Containerise all services with Docker, integrate with Kong API Gateway · Set up logging (Loki), metrics (Prometheus), tracing (Tempo) · Write API docs (Swagger) and deployment runbook · Train the Full Stack team on using the AI APIs --- REQUIREMENTS (Must Have): · Python (5+ years professional) · FastAPI or Flask (expert) · vLLM or TensorRT-LLM (production deployment) · RunPod, AWS SageMaker, or similar GPU cloud · Docker & Docker Compose (advanced) · Vector DBs (Qdrant, Pinecone, or Weaviate) · PostgreSQL with pgvector · Redis (caching + queue) · Git & CI/CD · Linux admin (Ubuntu, shell scripting) Nice to have: Llama/Qwen/DeepSeek experience, AWQ/GPTQ quantisation, NATS, Kong, Vault, Prometheus/Grafana/Loki/Tempo, MinIO/S3, Whisper, FLUX/Stable Diffusion. --- HOW TO APPLY: Send your application to Include: · CV/Resume highlighting Python AI production experience · GitHub/Portfolio with AI deployment projects · Brief intro video Subject Line: "Python AI Engineer - [Your Name]"