ML Inference Performance Engineer
Posted 21 Sep 2026
Advertised as “Intern - ML Inference Performance Engineer”
BranchFactor Summary
The original posting with the fluff stripped out
- Management level
- Individual contributor
- Employment
- Hybrid
- Contract
- Full-time
No salary listed for this role.
Field of studyComputer Engineering, Computer Science, Electrical Engineering (or related)
Study levelBachelor's or higher
About Us
Axelera AI is not your regular deep-tech company. We are creating the next-generation AI platform to support anyone who wants to help advancing humanity and improve the world around us.
In just five years, we have raised a total of $370 million and have built a world-class team of 250+ employees (including 60+ PhDs with more than 40,000 citations), both remotely from 20 different countries and with offices in Belgium, France, Switzerland, Italy, the UK, headquartered at the High Tech Campus in Eindhoven, Netherlands.
We have also launched our Metis™ AI Platform, which achieves a 3-5x increase in efficiency and performance, and have visibility into a strong business pipeline exceeding $100 million.
Our unwavering commitment to innovation has firmly established us as a global industry pioneer.
Are you up for the challenge?
Position Overview
We're looking for a curious, rigorous engineer to join our team and dig into the performance of ML inference systems. You'll work across the full inference stack — from model export and compiler toolchains to runtime execution on silicon — to build a clear, evidence-based picture of how different platforms perform and why.
Your work will go beyond running benchmarks: you'll develop a repeatable evaluation methodology, investigate performance bottlenecks at the hardware and software level, and build the tooling that transforms raw measurements into actionable insight. The findings you produce can directly shape our product decisions.
Key responsibilities:
-
Benchmarking & Tooling: Develop a thorough understanding of internal benchmarking tools covering throughput, latency, power, and accuracy across device-level, host-transaction, and end-to-end pipeline scenarios. Improve existing tooling, define reproducible procedures, and establish a standardised results format for rigorous cross-platform comparisons. Maintain a dedicated dashboard for performance visualisations.
-
Platform Evaluation: Research and evaluate AI accelerator products from various vendors, gaining hands-on experience with their SDKs, toolchains, flexibility, and limitations through a structured evaluation process. Track model support across platforms to identify strengths, gaps, and areas for improvement.
-
Pipeline Analysis: Characterise full inference pipelines, capturing host-device transaction overhead and end-to-end performance metrics. Ensure equivalent pipeline configurations across platforms using frameworks such as GStreamer to maintain methodological consistency.