ML Inference Performance Intern — Benchmarking & Tools

Axelera AI; Eindhoven; Hybrid; EUR 42,000 - 64,000; Full time

Benefits offered by this job

Pension plan

Employee insurances

Company shares

Job summary

Axelera AI is seeking 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—model export, compiler toolchains, and 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 bottlenecks at hardware and software levels, and build tooling that

Qualifications

• Currently enrolled in final years of Bachelor's or Master's programme or Masters thesis project.
• Proficiency in Python and C/C++ development.
• Experience with end-to-end computer vision pipelines.
• Familiarity with benchmarking concepts (performance, latency).
• Experience with inference tools, APIs, or SDKs (e.g., TensorRT).
• Understanding of deep learning model concepts (quantization, ONNX, PyTorch).
• Linux, Bash scripting, and Docker proficiency.
• Hands-on experience with embedded hosts.
• Strong written and verbal English communication.
• Good organisational skills.

Responsibilities

• Benchmarking & tooling: develop benchmarking tools for throughput, latency, power, and accuracy across platforms; maintain dashboards for visualisations.
• Platform evaluation: evaluate AI accelerators and vendor SDKs and track model support across platforms.
• Pipeline analysis: characterize full inference pipelines and ensure consistent configurations across platforms.
• Lab & infrastructure: set up lab hosts across hardware platforms and onboard new evaluation hardware.
• Reporting: synthesize findings into clear reports informing engineering and roadmap decisions.

Skills

Python

C/C++

CV pipelines

Benchmarking

Inference SDKs

DL concepts

Agentic AI

Git

LLM benchmarking

Linux

Bash scripting

Embedded hardware

English communication

Organisational skills

Education

Bachelor's or Master's in Computer Engineering/Computer Science/EE

Tools

TensorRT

GStreamer

Docker

Git

Job description

Axelera AI is seeking 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—model export, compiler toolchains, and 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 bottlenecks at hardware and software levels, and build tooling that