Data Science and Analytics · Cyprus

Machine Learning Engineer, AI Models

Tenstorrent · Cyprus · Posted Sep 26, 2025

This posting comes from Tenstorrent. Confirm the details on their site before applying.

Overview

Join Tenstorrent’s AI Models team and work at the layer most ML engineers never see: bringing advanced models to life on custom AI hardware. You’ll own real workloads end‑to‑end including porting, tuning, and validating LLMs and vision models on our accelerator, and chasing down every last millisecond and percentage point of accuracy. This role is for people who love the craft of ML engineering and want their work to matter at silicon scale, not just behind another API.

Responsibilities

  • How to bring state‑of‑the‑art LLMs and vision models to high performance on a custom AI accelerator.
  • How to trace and fix performance bottlenecks from PyTorch code down to kernels and memory systems.
  • How to turn research‑grade models into reliable, production deployments on new hardware.
  • The practical trade‑offs between techniques like quantization, FlashAttention, and kernel fusion when you’re optimizing real throughput, latency, and memory.
  • How your findings can drive changes across compiler, kernel, and hardware teams in a full‑stack co‑design loop

Requirements

  • Bring up, run, and debug modern ML models (e.g., transformers) using PyTorch or TensorFlow.
  • Analyze model behavior and performance, and identify bottlenecks across the stack.
  • Improve efficiency, correctness, and scalability of model execution in real systems.
  • Work closely with compiler, kernel, and hardware teams to drive performance and system-level improvements.
  • Help translate state-of-the-art model architectures into production-grade, high-performance deployments.
  • Strong experience building and working with ML models in PyTorch or TensorFlow.
  • Strong understanding of modern ML model architectures (ex: transformers).
  • Solid software engineering fundamentals with strong debugging and problem-solving skills.
  • Comfort working in a fast-moving, research-meets-engineering environment.
  • Bonus, not required: experience with profiling or performance tuning, or familiarity with quantization, flash attention, kernel fusion, memory hierarchies, C++, CUDA, or systems programming.

Benefits

  • Bonus

Great fits start here.

Whether you're looking for your next role or your next team member, give people and possibilities a place to meet.