Software Engineer Foundry Agent

Do you want to fine-tune OpenAI’s most advanced models on Azure — working with GPT-4.1, GPT-5, and beyond? From supervised fine-tuning (SFT) to reinforcement learning methods like DPO and others, this role puts you hands-on with the techniques shaping the future of AI. On this team, you’ll play a key role in improving the performance and reliability of customizing some of the world’s most advanced AI models. You’ll gain experience with fine-tuning workflows, experimenting with reinforcement learning techniques, and applying advanced optimization strategies that directly impact product quality. You’ll also work directly with the training code, debug complex behaviors, and sharpen the skills that make cutting-edge models more reliable and effective. The models you help shape will power critical workloads at some of the world’s leading companies. Microsoft’s mission is to empower every person and every organization on the planet to achieve more. As employees we come together with a growth mindset, innovate to empower others, and collaborate to realize our shared goals. Each day we build on our values of respect, integrity, and accountability to create a culture of inclusion where everyone can thrive at work and beyond. This role is targeting an immediate start date.