OpenAITL, Research Inference
San Francisco · 全职 · 算法与研究
需要对标的能力
上下文工程 · 记忆管理Agent 工程 · Harness / 脚手架AI Infra · 推理部署成本优化 · 性能调优评测 · Eval 方法论AI 工程设计模式
岗位职责与要求
ABOUT THE TEAM
The Foundations team focuses on how model behavior changes as we scale models, data, and compute. The team studies the interactions between model architecture, optimization, and training data, and uses those insights to guide how new models are designed and trained.
ABOUT THE ROLE
In this role, you will build the systems that enable advanced AI models to run efficiently at scale. You will operate at the intersection of model research and systems engineering, translating new architectural ideas into high-performance inference systems that surface real tradeoffs in performance, memory, and scalability.
Your work will directly influence how models are designed, evaluated, and iterated on across the research organization. By developing and evolving high-performance inference infrastructure, you will enable researchers to explore new ideas with a clear understanding of their computational and systems implications.
This is not a product-serving role. Instead, it is a research-enabling systems role focused on performance, correctness, and realism - ensuring that AI research is grounded in what can actually scale.
IN THIS ROLE, YOU WILL:
- Design and build high-performance inference runtimes for large-scale AI models, with a focus on efficiency, reliability, and scalability.
- Own and optimize core execution paths, including model execution, memory management, batching, and scheduling.
- Develop and improve distributed inference across multiple GPUs, including parallelism strategies, communication patterns, and runtime coordination.
- Implement and optimize inference-critical operators and kernels informed by real-world workloads.
- Partner closely with research teams to ensure new model architectures are supported accurately and efficiently in inference systems.
- Diagnose and resolve performance bottlenecks through profiling, benchmarking, and low-level debugging.
- Contribute to observability, correctness, and reliability of large-scale AI systems.
YOU MIGHT THRIVE IN THIS ROLE IF YOU:
- Have experience building production inference systems, not just training or running models.
- Are comfortable with GPU-centric performance engineering, including memory behavior and latency/throughput tradeoffs.
- Have worked on multi-GPU or distributed systems involving batching, scheduling, or runtime coordination.
- Can reason end-to-end about inference pipelines, from request handling through execution and output streaming.
- Are able to understand research ideas and implement them within real system and performance constraints.
- Enjoy solving hard, ambiguous systems problems that only emerge at scale.
- Prefer hands-on technical ownership and execution over abstract design work.
To notify OpenAI that you believe this job posting is non-compliant, please submit a report through this form https://form.asana.com/?d=57018692298241&k=5MqR40fZd7jlxVUh5J-UeA. No response will be provided to inquiries unrelated to job posting compliance.
At OpenAI, we believe artificial intelligence has the potential to help people solve immense global challenges, and we want the upside of AI to be widely shared. Join us in shaping the future of technology.
查看中文参考译文
关于团队
Foundations 团队专注于研究模型行为如何随模型规模、数据量和计算资源的扩展而变化。该团队研究模型架构、优化和训练数据之间的相互作用，并利用这些洞见来指导新模型的设计和训练。
关于职位
在此职位中，你将构建使高级 AI 模型能够高效大规模运行的系统。你将在模型研究与系统工程之间的交叉领域工作，将新的架构理念转化为高性能的 inference 系统，并在性能、内存和可扩展性方面呈现真实的权衡。
你的工作将直接影响整个研究组织中模型的设计、评估和迭代方式。通过开发和演进高性能的 inference 基础设施，你将使研究人员能够在清楚了解其计算和系统影响的情况下探索新想法。
这不是一个面向产品服务的职位，而是一个以性能、正确性和真实性为核心的研究赋能系统职位——确保 AI 研究立足于实际可扩展的范围内。
在此职位中，你将：
- 为大规模 AI 模型设计和构建高性能的 inference runtime，注重效率、可靠性和可扩展性。
- 负责并优化核心执行路径，包括模型执行、内存管理、batching 和 scheduling。
- 开发和改进跨多个 GPU 的分布式 inference，包括并行策略、通信模式和 runtime 协调。
- 基于实际工作负载，实现和优化对 inference 至关重要的 operator 和 kernel。
- 与研究团队紧密合作，确保新的模型架构在 inference 系统中得到准确且高效的支持。
- 通过 profiling、benchmarking 和低级别 debugging，诊断并解决性能瓶颈。
- 为大规模 AI 系统的可观测性、正确性和可靠性做出贡献。
如果你具备以下条件，你可能适合这个职位：
- 有构建生产级 inference 系统的经验，而不仅仅是训练或运行模型。
- 熟悉以 GPU 为中心的性能工程，包括内存行为以及延迟/吞吐量权衡。
- 有涉及 batching、scheduling 或 runtime 协调的多 GPU 或分布式系统工作经验。
- 能够对 inference pipeline 进行端到端分析，从请求处理到执行再到输出流式传输。
- 能够理解研究理念，并在实际系统和性能约束内实现它们。
- 喜欢解决只有在规模下才会出现的困难且模糊的系统问题。
- 更倾向于亲自动手的技术主导和执行，而非抽象的设计工作。
如需通知 OpenAI 你认为此职位发布不合规，请通过此表单提交报告 https://form.asana.com/?d=57018692298241&k=5MqR40fZd7jlxVUh5J-UeA。与职位发布合规性无关的询问将不予回复。
在 OpenAI，我们相信人工智能有潜力帮助人们解决巨大的全球挑战，我们希望 AI 带来的益处能够被广泛分享。加入我们，共同塑造技术的未来。
译文仅供辅助阅读，具体要求以原始招聘来源为准。