10 inference engineering leaders
Engineering Director, Serving and Inference, Director - Inference and Senior Manager - Inference are among the current titles held by these ten inference engineering leaders, at companies including Meta, CoreWeave and LinkedIn. A reader can learn how inference engineering leaders approach their work from people who have held the role.
Professionals to explore
Anish Asthana
LinkedInExperience: Engineering Manager | AI Inference Engineering · Red Hat
Anish Asthana has been Engineering Manager | AI Inference Engineering at Red Hat since September 2025, based in Boston. At Red Hat, Anish Asthana was Engineering Manager | OpenShift AI in 2025, Engineering Associate Manager | OpenShift AI from 2023 to 2025 and Senior Software Engineer | AI Services from 2021 to 2023.
Denis-Gabriel Vieriu
LinkedInExperience: ML Engineering Manager - Distributed inference · Apple
Denis-Gabriel Vieriu has been ML Engineering Manager - Distributed inference at Apple since July 2026, based in the San Francisco Bay Area. At Apple, Denis-Gabriel Vieriu was Staff Machine Learning Engineer from 2021 to 2026 and GPU Software Engineer from 2019 to 2021, and describes building large-scale AI infrastructure and high-performance inference systems.
Hagay Lupesko
LinkedInExperience: Senior Vice President, AI Inference · Cerebras
Hagay Lupesko has been Senior Vice President, AI Inference at Cerebras since September 2024 and describes building AI inference for both cloud and on-prem use. Hagay Lupesko was VP of Software Engineering, MosaicML (acquired by Databricks) at Databricks Mosaic Research from 2022 to 2024, Director of Engineering, Meta AI at Meta from 2019 to 2022 and Engineering Leader, Deep Learning at Amazon Web Services (AWS) from 2017 to 2019.
Jacob Visovatti
LinkedInExperience: Director of Engineering, AI Inference · Deepgram
Jacob Visovatti has been Director of Engineering, AI Inference at Deepgram since April 2026 and was Senior Engineering Manager, AI Inference there from 2023 to 2026, based in the Detroit area. Jacob Visovatti describes leading AI inference engineering from customer-facing APIs down to low-level inference on GPUs, including inference optimization and bringing new inference products to market.
Jun Wan
LinkedInExperience: Senior Manager, Deep Learning Inference · NVIDIA
Jun Wan has been Senior Manager, Deep Learning Inference at NVIDIA since July 2026, based in Boston. Jun Wan was Senior Software Development Manager, Amazon General Intelligence at Amazon from 2025 to 2026 and Software Development Manager, Amazon General Intelligence Foundations there from 2023 to 2025, and describes building and scaling production-grade inference systems.
Mike Ching
LinkedInExperience: Engineering Director, Serving and Inference · Meta
Mike Ching has been Engineering Director, Serving and Inference at Meta since January 2024, with a profile headline covering core serving, model inference and training platform for Facebook and Instagram, based in the San Francisco Bay Area. Mike Ching was Engineering Director, AI Infrastructure at Instagram from 2022 to 2023, Engineering Director, Training Platform at Facebook from 2020 to 2022 and Engineering Director, Cloud Storage at Google from 2017 to 2020.
Nancy Zheng
LinkedInExperience: Vice President, AI Inference · Cerebras
Nancy Zheng has been Vice President, AI Inference at Cerebras since March 2026, based in Mountain View, California, and describes building disaggregated inference. Nancy Zheng was Co-Founder, CTO at Hachi AI from 2024 to 2025, Engineering Director at Stripe from 2021 to 2023 and Engineering Leader at Google from 2011 to 2021.
Qing Lan
LinkedInExperience: Senior Manager - Inference · LinkedIn
Qing Lan has been Senior Manager - Inference at LinkedIn since August 2026 and was Tech Lead Manager - LLM Inference there from 2024 to 2026, based in Mountain View, California. Qing Lan describes leading work on efficient inference solutions and building an inference engine to optimize GenAI platforms across GPU resources, and was Tech Lead Manager at Amazon Web Services (AWS) from 2023 to 2024.
Sitanshu Gupta
LinkedInExperience: Director - Inference · CoreWeave
Sitanshu Gupta has been Director - Inference at CoreWeave since March 2026, based in the San Francisco Bay Area. Sitanshu Gupta was Senior Software Development Manager at Annapurna Labs (AWS-Amazon) from 2024 to 2026, Director at SambaNova from 2017 to 2024 and Principal Engineer at Oracle from 2011 to 2017, and describes work across distributed training and inference.
Sri Krishna Vempati
LinkedInExperience: Engineering Manager, AI Model Serving Platform · Netflix
Sri Krishna Vempati has been Engineering Manager, AI Model Serving Platform at Netflix since January 2025, based in Mountain View, California. At Netflix, Sri Krishna Vempati was Engineering Manager and Technical Lead, Personalization ML Serving System from 2023 to 2024 and Software Engineer - 6, Messaging Platform & Personalization from 2019 to 2023, and was Co-Founder and CTO at Multitudes in 2019.
Choose the right perspective
Pick the person whose own role, team scope and kind of company sit closest to the decision you face. Check the dates on each role to see how long each person has led inference or model serving work.
Questions to take into the conversation
- 01What did you focus on first when you took on your current inference or model serving role, and why?
- 02How have you organized your team and divided work with research and platform groups?
- 03Which measures do you review regularly to judge how your serving systems are performing?
Reaching inference engineering leaders
How can I contact one of these inference engineering leaders?
Pick one of the 10 people on this page and choose "Book a paid call", or describe your project to find others. You offer a fee for a 15-minute call or a written answer, Instant Expert finds the person's work email and sends the invitation, and they decide whether to accept. The list covers 9 companies, including Red Hat, Apple and Cerebras, based on profile data retrieved on October 22, 2026. Being listed here doesn't mean someone has agreed to take calls.
How much does it cost to reach inference engineering leaders?
You choose the offer, starting at $5 per person. The offer is what the person receives, and Instant Expert's fee is added on top, so a $100 offer costs you $125. The fee is 20% of what you pay. You're charged only when the person books the call or sends the answer.
What if they don't reply?
You pay nothing. Instant Expert sends follow-up reminders, and if the person hasn't booked or answered within 7 days, the request expires and any hold on your card is released. You can invite several of the 10 people on this list at once and cap your total spend, so you pay only for the ones who accept.
Can an AI agent ask one of these inference engineering leaders a question?
Yes. An agent with a USDC wallet on Base can ask one question without an Instant Expert account. It names the person, for example by the LinkedIn URL on this page, and pays per ask over x402 (HTTP 402). The person answers in writing or by voice note, and if nobody answers within 7 days, the payment goes back to the wallet automatically. Claude and ChatGPT can do the same through the Instant Expert connector: setup is at /docs/mcp for Claude and /docs/chatgpt for ChatGPT. x402 docs
About this directory
This is a professional research starting point based on business profile data retrieved on . Titles and companies reflect that source snapshot; roles marked former had ended by then. Check the linked profiles for current details. Inclusion does not imply Instant Expert membership or availability.
Request a correction or removal