Artificial intelligence news.
Straight from the original announcements.

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

October 27, 2026, 19:14By the AI News Bites Editorial TeamSource: Baseten
Baseten hires four engineering leaders from Google, Meta, Anyscale and Databricks
Image: Baseten

Baseten has brought on four engineering leaders: Bryan Vann, Ilina Mitra, Jaikumar Ganesh and Rahmi Marasli. According to the company, they will help grow its engineering organization as it supports customers' AI workloads.

Key points
  • Baseten has hired Bryan Vann, Ilina Mitra, Jaikumar Ganesh and Rahmi Marasli as engineering leaders.
  • Vann joins the Baseten Inference Stack team from Kindo; Mitra becomes Head of Inference Platform after leading PyTorch Inference Acceleration at Meta.
  • Ganesh, formerly Head of Engineering at Anyscale, will work with the forward-deployed engineering team.
  • Marasli becomes Head of Product Platform, coming from NexHealth, with prior roles at Databricks and Google.
  • Baseten says it is still hiring in inference, model performance, infrastructure, product platform and forward-deployed engineering.

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.

BasetenBryan VannIlina MitraJaikumar GaneshRahmi MarasliKindoenterprise AIcloud

Related news

AWS details four ways to speed up Amazon Bedrock AgentCore sessions
For developersNovember 13, 2026, 23:02

AWS details four ways to speed up Amazon Bedrock AgentCore sessions

AWS has outlined four architecture patterns for reducing session startup delays in Amazon Bedrock AgentCore runtime, including snapshot-based initialization, build hooks…

AWS adds three-tier Data Capture to SageMaker HyperPod
Products and toolsNovember 13, 2026, 19:01

AWS adds three-tier Data Capture to SageMaker HyperPod

Amazon SageMaker HyperPod now includes Data Capture, a built-in capability that records live inference inputs and outputs to Amazon S3. AWS says the feature is designed…

Dynatrace and Microsoft bring observability context to Azure AI workflows
Products and toolsNovember 13, 2026, 18:36

Dynatrace and Microsoft bring observability context to Azure AI workflows

Dynatrace will showcase integrations with Microsoft tools that bring observability data into AI-assisted development, Azure AI applications and cloud operations. The…