Job Description

Our partner is looking for Mid and Senior AI Engineers to work on AI models and deployment frameworks close to the hardware layer.

You will research and prototype modern neural network architectures, optimize models for efficient hardware execution and help improve how AI workloads are deployed on advanced processor platforms.

Location: Barcelona, Spain, Hybrid
Level: Mid / Senior

Responsibilities

Research and prototype neural network architectures
Optimize models for hardware deployment
Apply quantization, pruning and compression
Analyze model performance and efficiency
Work with AI frameworks close to the hardware layer
Support production AI model development and deployment
Collaborate with software and hardware engineering teams

Requirements

Strong understanding of transformers, CNNs, vision models and RNNs
Quantization, pruning and compression
AI model performance analysis
PyTorch
C++
Git and CI/CD
Strong problem solving skills
English C1

Optional / Desired

RISC V experience
MLIR
ONNX Runtime
Kernel development
Perfetto or similar tracing tools
Model accuracy tracking
AI application deployment
CUDA or ROCm
OpenXLA, TVM or IREE
TensorFlow
vLLM, SGLang, Triton or DeepSpeed
TensorRT
pybind11
GDB and software profiling

What’s in it for you?

Flexible working hours
Hybrid model, 4 days office, 1 day from home
1 week per year working from anywhere
25 days annual leave plus December 24 and 31
Monthly food allowance
Private medical insurance
Relocation bonus
Housing search support
Visa support if required
Family relocation support
Virtual shares
Language classes
Tax incentive, subject to eligibility

Similar jobs