Baseten hires four engineering leaders from Google, Meta, Anyscale and Databricks

Inference stack and platform get experienced leaders

Bryan Vann joins the Baseten Inference Stack (BIS) team from Kindo, where he was co-founder and CTO. Before that he spent sixteen years at Google, where he was an original architect of Google Drive and later led much of its engineering organization as Senior Director. Baseten describes BIS as the platform that serves models efficiently and reliably in production, and says Vann will apply his experience to it.

Ilina Mitra joins as Head of Inference Platform. She comes from Meta, where she led the PyTorch Inference Acceleration organization. According to Baseten, her team was responsible for optimizing Meta's most critical recommendation and generative AI models and bringing them into production. At Baseten she will help grow the inference platform and the teams behind it, as customers' workloads increase in scale and complexity.

Customer-facing engineering and product platform

Jaikumar Ganesh joins from Anyscale, where he was Head of Engineering. Baseten says he helped build the engineering team behind Ray and Anyscale and played a direct role in winning the company's earliest customers. He previously spent 7 years at Uber, leading Applied ML and ML Infrastructure, with work on problems such as ETA prediction and location accuracy, and he started the Uber Bengaluru Engineering Office. Earlier, he was part of the Android 1.0 team at Google.

At Baseten, Ganesh will work with the forward-deployed engineering team, which works closely with customers on their hardest inference problems.

Rahmi Marasli joins as Head of Product Platform. He was most recently Head of Engineering at NexHealth. Before that, he led development of Databricks' commercialization platform and spent nearly 15 years at Google building AI and ML platforms. Baseten says he will help strengthen the foundations that support its products and let its engineering teams move quickly. The company ties this to its goal of developing the most secure and scalable enterprise platform for inference, training, and agents.

Hiring continues across engineering

Baseten says the four leaders bring technical judgment and experience that will help it grow both its systems and its teams. The company adds that it is continuing to hire across engineering, including inference, model performance, infrastructure, product platform, and forward-deployed engineering.

For customers running demanding AI workloads, the appointments signal where Baseten is putting its effort: the production serving stack, the inference platform, hands-on work with customers, and the enterprise product platform. The source does not give details on specific product changes or timelines tied to the hires.