Inference is just one piece of an effective background agent. Let's design and build the rest of the system that turns billions of tokens into the best possible answers. What you’ll do: Design custom evals for multi-turn, massively parallel agents. Build agent harnesses to improve open model (Deepseek, Qwen, Llama) performance. Automate prompt optimization techniques like DSPy. What we’re looking for: Experience building AI agents. Familiarity with open source models.