AI Engineer

About the roleWe are seeking an AI Engineer to build and implement AI systems for content production at scale. You'll work at the intersection of engineering and content designing prompt pipelines, integrating generative models, and building the tooling that turns source material into finished creative output. The ideal candidate is technically strong but also has taste: someone who understands story and craft, and can tell the difference between output that's technically correct and output that's actually good.ResponsibilitiesBuild and iterate on prompt pipelines and multi-agent workflow componentsDesign and integrate agentic workflows orchestrate multi-step, tool-using agents that plan, call models, and hand off between stages in productionDeploy and serve open-source models set up inference endpoints, manage GPU compute, and optimize for latency and costWrite evals compare outputs against references, quantify quality, and feed results back into the pipelineWork on data pipelines: structured extraction from messy source text, localization, similarity/dedupDebug and maintain pipeline stages in productionWhat you bring:  (1+/3+) years of engineering experience, or a strong portfolio of shipped projectsSolid Python fundamentals clean, working, readable codeHands-on experience with LLM APIs and prompt engineering (personal projects count)Comfort with Git, REST APIs, and working in a Linux environmentA feel for content and narrative you can judge whether generated output is actually good, not just validCuriosity and clear communication you ask good questions and don't stay stuck silently PreferredExposure to agent/orchestration frameworks (LangGraph, LangChain, CrewAI)Familiarity with vector databases, embeddings, or RAG (Qdrant, pgvector)Hands-on work with open-source generative media models Flux, LTX, Wan, or similarExperience deploying open-source models for inference (vLLM, ComfyUI, Replicate/Cog, Docker + GPU)Experience writing evals or LLM-as-judge scoringNode.js and Fastapi familiarity, or experience deploying on AWS