PeopleofSuperintelligence

Builder

Chris Leary

Chris Leary is a software engineer whose AI work spans compilers and accelerator hardware. He co-authored a Tensor Processing Unit study and presented XLA's TensorFlow compiler work with Todd Wang in 2017. His 2018 JAX paper described a tracing compiler for Python and NumPy, and his later Google talks covered XLA, JAX and XLS hardware synthesis. As of October 2026, he is a Member of Technical Staff at OpenAI and presents its Jalapeño inference chip.

Now at
OpenAI
Works
7
Citations
6,075
h-index
6

Publication numbers from OpenAlex, as of 19 October 2026.

Timeline

  1. March 2017

    XLA for TensorFlow

    At the TensorFlow Developer Summit in 2017, he and Todd Wang explain how TensorFlow uses XLA, JIT and ahead-of-time compilation to reduce execution time.

  2. April 2017

    A Tensor Processing Unit study

    He co-authors a 2017 study that evaluates a datacenter Tensor Processing Unit for neural-network inference and compares it with server CPUs and GPUs.

  3. 2018

    JAX and high-level tracing

    He co-authors a 2018 SysML paper that describes JAX as a tracing JIT compiler for Python and NumPy machine-learning programs, with XLA generating optimized accelerator code.

  4. March 2022

    XLA, JAX and XLS

    At Cornell's LATTE accelerator-design workshop in March 2022, he recounts a decade of development across XLA, JAX and XLS, with acceleration targets at data-center scale.

  5. October 2022

    Formal methods in XLS

    At ADAPTOR in October 2022, he gives a keynote on XLS, a high-level synthesis toolchain for hardware blocks, and discusses equivalence checking and floating-point verification.

  6. As of October 2026

    OpenAI hardware presentation

    He is a Member of Technical Staff at OpenAI and presents its Jalapeño inference chip at Hot Chips 2026.

Career

  1. NowOpenAIMember of Technical Staff
  2. 2016–2024Google

From the biography and OpenAlex affiliations (the years of papers that list the organization), so some years are approximate.

Most-cited works

  1. In-Datacenter Performance Analysis of a Tensor Processing Unit2017 · International Symposium on Computer Architecture · 4,527 citationsWith Vijay Vasudevan
  2. Compiling machine learning programs via high-level tracing2018 · 177 citations
  3. gpucc: an open-source GPGPU compiler2016 · International Symposium on Code Generation and Optimization (CGO) · 63 citations
  4. A Hardware Accelerator for Protocol Buffers2021 · 44 citations
  5. Subgraph Extraction-Based Feedback-Guided Iterative Scheduling for HLS2024 · 1 citations

From OpenAlex, as of 19 October 2026.

  1. 13 of 79 people shaping AI with a former OpenAI role now work at AnthropicIncludes Chris Leary. Our estimates of where OpenAI recruits came from and where people with former OpenAI roles work now.
  2. The median h-index is 53 at universities and 19 at frontier AI labsIncludes Chris Leary. The median h-index is 53 at universities and 19 at frontier AI labs. We compare publishing careers, citations and moves to estimate how universities and frontier labs contribute to AI research.
  3. Google alumni founded or led 87 other organizations, the most among the labs we compareIncludes Chris Leary. We trace 212 organizations founded or led by AI lab alumni, and 223 career moves between the labs.
  4. 44% of AI career moves go from one university to anotherIncludes OpenAI. We estimate how 14,272 AI career moves link universities, companies, labs and government research centers, with net flows and the most common paths.

Colleagues

People with dated positions at the same organization in the same years.

Sources and credits

Photo: We have no published photo of Chris Leary yet. Send us a free-licensed photo.

  1. XLA - TensorFlow, compiled developers.googleblog.com. Checked 19 October 2026.
  2. In-Datacenter Performance Analysis of a Tensor Processing Unit arxiv.org. Checked 19 October 2026.
  3. Compiling machine learning programs via high-level tracing research.google. Checked 19 October 2026.
  4. LATTE '22 Workshop on Languages, Tools, and Techniques for Accelerator Design capra.cs.cornell.edu. Checked 19 October 2026.
  5. ADAPTOR 2022 adaptor-workshop.github.io. Checked 19 October 2026.
  6. Hot Chips 2026 hc2026.hotchips.org. Checked 19 October 2026.
  7. Hot Chips: OpenAI Jalapeno Presentation taekim.substack.com. Checked 19 October 2026.