AI Systems Engineer

## Senior AI Systems & Integration Engineer *Job Type:* Contract / Project-Based *Location:* Remote (AEDT/Flexible overlap preferred) *Project Scope:* End-to-end AI component orchestration, enterprise integration, retrieval pipelines, and full-stack AI system deployment. --- It's is an advanced technology platform delivering high-performance software products, automated content engines, and enterprise-grade technical solutions. We focus on clean solution architecture, robust component integration, and scalable AI governance rather than raw model pre-training. We are looking for a top-tier, hands-on AI Engineer who can take ownership of our entire AI stack—from vector databases and LLM orchestration to high-throughput API services and production deployment. --- ### Role Overview We need an exceptional, pragmatic AI Engineer who can bridge the gap between cutting-edge AI models (OpenAI, Anthropic, open-weights via Ollama/vLLM) and enterprise production systems. You will not be training foundational models from scratch; instead, you will architect, build, and optimize the inflow, outflow, and governance of AI components within our existing tech stack. You will work closely with our core infrastructure running on *Next.js, FastAPI, PostgreSQL with pgvector, Redis, and Docker*, deployed via Cloudflare Tunnels on an M4 Mac Mini production server. --- ### Key Responsibilities * *AI Orchestration & RAG Pipelines:* Design, build, and optimize robust Retrieval-Augmented Generation (RAG) systems, semantic search, and context injection workflows using PostgreSQL (pgvector) and vector embedding models. * *LLM Integration & Agent Workflows:* Implement reliable function-calling, structured JSON outputs, multi-agent coordination, and prompt engineering pipelines using Python (FastAPI) and modern LLM frameworks. * *Full-Stack Integration:* Connect AI backend services seamlessly with Next.js frontends and automated media/video rendering pipelines (Python/Node.js, FFmpeg, Remotion). * *System Governance & Performance:* Ensure low latency, robust error handling, cost optimization, and secure rate-limiting across all LLM and vector operations. * *Production Deployment:* Containerize services using Docker and integrate them into our existing Caddy/Cloudflare production environment with clean logging and monitoring. --- ### Technical Requirements & Stack Proficiency * *Core Languages:* Advanced Python (FastAPI, async operations) and TypeScript/JavaScript (Next.js). * *AI/ML Ecosystem:* Extensive experience with LangChain, LlamaIndex, or custom orchestration frameworks; hands-on implementation of vector search (pgvector, Pinecone, or Qdrant). * *Databases & Caching:* PostgreSQL, Redis. * *Infrastructure & DevOps:* Docker, Linux environments, API security, and reverse proxies (Caddy/Nginx). * *Architecture Mindset:* Strong grasp of component-level design, decoupling services, clean API contracts, and robust exception handling. --- ### What We Are Looking For (Qualities) * *Pragmatic & Execution-Focused:* You prioritize clean, maintainable, production-ready code over theoretical proofs or over-engineered abstractions. * *Autonomous Problem Solver:* You can take a high-level architectural goal and independently design, test, and deploy the complete component loop. * *Clear Communicator:* Able to explain technical trade-offs clearly and document integration patterns effectively. --- ### Application Requirements When applying for this role on Upwork, please include: 1. A brief summary of your most complex RAG or AI integration project, specifically mentioning the database and backend framework used. 2. Code snippets or GitHub links demonstrating clean Python/FastAPI or TypeScript integration work. 3. Your typical availability (hours/week) and timezone.