---
title: 'Intern - ML Inference Performance Engineer at Axelera AI'
canonical: 'https://feeny.ai/job/intern-ml-inference-performance-engineer-axelera-ai-eindhoven-6wpcpcnp1jwd'
type: 'job'
last_seen: '2026-10-17'
---

# Intern - ML Inference Performance Engineer at Axelera AI

- **Company:** Axelera AI
- **Location:** Eindhoven, Netherlands
- **Employment:** full-time
- **Work type:** hybrid
- **Posted:** 2026-09-21
- **Last confirmed live:** 2026-10-17
- **Apply:** https://jobs.ashbyhq.com/axelera/5d48cd6c-5c5b-45e2-973e-1017a70a5485

## Job description

## About Us

[Axelera AI](https://www.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.
- Lab & Infrastructure: Set up and maintain lab hosts across multiple hardware platforms and support the onboarding of new evaluation hardware.
- Reporting: Synthesise findings into clear, structured reports that directly inform engineering and roadmap decisions.

Requirements:

- Currently enrolled in the final years of a Bachelor's programme or in a Master's programme in Computer Engineering, Electrical Engineering, Computer Science, or a related field. This position may also be carried out as a Master's thesis project.
- Python development experience
- C/C++ knowledge
- Experience with end-to-end computer vision pipelines
- Familiarity with benchmarking concepts (performance, latency, etc.)
- Experience with inference tools, APIs, or SDKs (e.g., TensorRT)
- Familiarity with deep learning model concepts (quantization, ONNX, PyTorch, etc.)
- Development experience using agentic AI
- Knowledge of version control (Git)
- Familiarity with LLM benchmarking concepts
- Proficiency with Linux, Bash scripting, and Docker
- Hands-on experience with embedded hosts
- Proficient written and verbal communication skills in English, with the ability to document findings clearly and precisely.
- Good organizational skills

Nice to have:

- GStreamer knowledge
- Basic GUI design experience

Location Work from our Axelera AI office in Eindhoven (Netherlands).

## What we offer

This is your chance to shape and be part of a dynamic, fast-growing, international organization. We offer an attractive compensation package, including a pension plan, extensive employee insurances and the option to get company shares. An open culture that supports creativity and continual innovation is awaiting you. Collaborative ownership and freedom with responsibility is characteristic for the way we act and work as a team.

At Axelera AI, we wholeheartedly embrace equal opportunity and hold diversity in the highest regard. Our steadfast commitment is to cultivate a warm and inclusive environment that empowers and celebrates every member of our team. We welcome applicants from all backgrounds to join us in shaping the future of AI.

## About Axelera AI

## Company Overview
- **One-liner**: Axelera AI develops cutting-edge AI hardware and software platforms for accelerating inference at the edge, using proprietary digital in-memory computing technology.
- **Entity Type**: Private (Series C)
- **Headquarters**: Eindhoven, Netherlands
- **Founded**: 2021
- **Founders**: Not publicly listed on primary sources

## Core Business
- **Primary industry/industries**: AI Hardware (Semiconductors), Edge AI Inference, Computer Vision
- **Target customers**: B2B, Enterprise, and SMBs across industrial manufacturing, security & surveillance, retail, robotics, and healthcare
- **Mission or purpose statement**: "To lead the democratization of Artificial Intelligence, offering faster, easy-to-use AI acceleration while minimizing power and cost, to simplify AI at the Edge." [axelera.ai](https://axelera.ai/our-story)

## Products & Services
- **Metis® AIPU (AI Processing Unit)**: A family of edge inference accelerators starting at 214 TOPs, available in M.2 and PCIe form factors (1-AIPU and 4-AIPU cards). Delivers 15 TOPs/W energy efficiency. [axelera.ai](https://axelera.ai/)
- **Europa® AIPU**: A higher-performance AI accelerator (629 TOPs) for demanding edge and near-edge workloads, setting a new industry benchmark for performance, power efficiency, and affordability. [axelera.ai](https://axelera.ai/)
- **Titania® Chiplet**: A future chiplet designed to scale the D-IMC architecture from edge to cloud. [axelera.ai](https://axelera.ai/our-story)
- **Voyager® SDK**: A software development kit with 100+ pre-optimized models, enabling deployment from model to production in hours, not weeks. [axelera.ai](https://axelera.ai/)
- **Metis AI Platform**: Complete edge AI systems (M.2 and PCIe accelerator cards) bundling the Metis AIPU with the Voyager SDK for computer vision applications. [axelera.ai](https://axelera.ai/)

## Market Standing
- **Valuation/Market Cap**: Not disclosed
- **Total Funding**: Over $450 million in equity, grants, and venture debt since founding (July 2021). This includes a $250M+ Series C (the largest investment ever in an EU AI semiconductor company), led by Innovation Industries, with new investors BlackRock and SiteGround Capital. [axelera.ai](https://axelera.ai/our-story)
- **Key Metric**: Total funding of $468.21M (per CB Insights). [cbinsights.com](https://www.cbinsights.com/company/axelera-ai)
- **Notable Investors/Partners**: Innovation Industries, European Innovation Council Fund, Invest-NL, Samsung Catalyst Fund, Verve Ventures, CDP Venture Capital SGR, Bitfury, Federal Holding and Investment Company of Belgium (SFPIM), imec, BlackRock, SiteGround Capital. [axelera.ai](https://axelera.ai/our-story)
- **Growth Signals**: Ranked #3 in the Emerging Enterprise (201-999 Employees) category on Fast Company’s 2026 Most Innovative Companies list. Has taped out four chips since founding. Announced the Europa AIPU and Titania chiplet. Secured up to €61.6m from the EuroHPC DARE project. [axelera.ai](https://axelera.ai/our-story)

## Competitive Advantages
- **Proprietary Digital In-Memory Computing (D-IMC)**: Performs matrix-vector multiplications in-place, eliminating data movement and delivering 50+ TOPs per core at FP32-equivalent accuracy. [axelera.ai](https://axelera.ai/)
- **Industry-Leading Energy Efficiency**: 15 TOPs/W, enabling high-performance AI inference at the edge without power or thermal constraints. [axelera.ai](https://axelera.ai/)
- **Full-Stack Solution**: Combines purpose-built hardware (AIPUs) with the Voyager SDK (100+ models, post-training quantization) for rapid deployment, significantly reducing time-to-value compared to GPU-based alternatives. [axelera.ai](https://axelera.ai/)
- **Scalable Architecture**: D-IMC and RISC-V dataflow architecture scales from edge to cloud via the Titania chiplet roadmap. [axelera.ai](https://axelera.ai/our-story)

## Strategic Focus
- **Democratizing AI**: Making high-performance AI inference accessible, affordable, and energy-efficient for any environment (edge to cloud). [axelera.ai](https://axelera.ai/our-story)
- **Commercial Expansion**: Scaling global commercial growth following the $250M+ Series C, with a focus on building out sales and field application engineering teams in EMEA and the Americas. [axelera.ai](https://axelera.ai/careers)
- **Ecosystem & Partnerships**: Recently announced six new partnerships to expand the edge AI ecosystem. [axelera.ai](https://axelera.ai/)
- **Product Roadmap**: Scaling the D-IMC platform from edge (Metis) to near-edge (Europa) to cloud (Titania chiplet), targeting a full range of inference use cases. [axelera.ai](https://axelera.ai/our-story)

## Why Work Here
- **High-Growth Environment**: A well-funded deep-tech startup (over $450M raised) with rapid commercial traction, ranked #3 on Fast Company’s 2026 Most Innovative Companies list. [axelera.ai](https://axelera.ai/careers)
- **Global & Remote-First Culture**: 248+ talented colleagues from 34 nationalities across 18 locations, with a strong remote/hybrid work policy. [axelera.ai](https://axelera.ai/careers)
- **Cutting-Edge Technology**: Work on proprietary D-IMC and RISC-V dataflow architecture, with a roadmap spanning edge to cloud. The team includes 39 PhDs. [axelera.ai](https://axelera.ai/careers)
- **Benefits**: Remote/flexible work, premium insurance, commute benefit, team-building activities, premium pension, work-life balance, cutting-edge equipment, fresh fruit at the office, and modern facilities. [axelera.ai](https://axelera.ai/careers)
- **Values-Driven Culture**: Values include "Think," "Focus on the Customer," "Move Fast," "Communicate Openly," and "Agree & Commit." Emphasis on freedom with responsibility. [axelera.ai](https://axelera.ai/careers)
- **Diverse & International**: 34 nationalities, average age 50+, with offices in Belgium, France, Switzerland, Italy, the UK, and headquarters in Eindhoven. [axelera.ai](https://axelera.ai/careers)

## Sources
1. [axelera.ai](https://axelera.ai/)
2. [axelera.ai](https://axelera.ai/our-story)
3. [axelera.ai](https://axelera.ai/careers)
4. [cbinsights.com](https://www.cbinsights.com/company/axelera-ai)
5. [jobs.ashbyhq.com](https://jobs.ashbyhq.com/axelera)

## Other roles at Axelera AI

- [Partner Marketing Manager, Global Accounts](https://feeny.ai/job/partner-marketing-manager-global-accounts-axelera-ai-united-states-b134rcq68mbm) — United States
- [Developer Relations and Community Manager](https://feeny.ai/job/developer-relations-and-community-manager-axelera-ai-europe-incl-uk-f0e7vjhj3p4w) — Europe (incl. UK)
- [Intern - AIPU Board Development](https://feeny.ai/job/intern-aipu-board-development-axelera-ai-florence-gxd0t9xq208q) — Florence, Italy
- [(Senior) Director of Sales - Enterprise AI](https://feeny.ai/job/senior-director-of-sales-enterprise-ai-axelera-ai-california-4t1n391zg2pp) — California
- [(Senior) Field Application Engineer - India](https://feeny.ai/job/senior-field-application-engineer-india-axelera-ai-india-tjpzd0600zy2) — India
- [Ecosystem Integration Engineer](https://feeny.ai/job/ecosystem-integration-engineer-axelera-ai-taiwan-8ymx2171c956) — Taiwan
- [Director - Hardware Engineering, AI Infrastructure Systems](https://feeny.ai/job/director-hardware-engineering-ai-infrastructure-systems-axelera-ai-europe-incl-e4ab9s5wg45n) — Europe (incl. UK)