> Markdown version of [/jobs/ext/4597440-computer-vision-edge-ai-engineer](https://www.wearedevelopers.com/jobs/ext/4597440-computer-vision-edge-ai-engineer). Every page supports `.md` or `Accept: text/markdown`. Links point to the HTML versions so they work for humans too. Agent guide: [/agents.md](https://www.wearedevelopers.com/agents.md).

---

# Computer Vision & Edge AI Engineer

- **Company:** Nvidia
- **Location:** Madrid, Spain
- **Contract:** Permanent contract
- **Skills:** Computer Vision, Microsoft Azure, C++ (Programming Language), Profiling, Nvidia CUDA, Software Debugging, Linux, Memory Management, Fault Tolerance, Python (Programming Language), Open Source Technology, Inference Optimization, Real Time Systems, Pytorch, Git, ONNX (Open Neural Network Exchange) Format, Triton Inference Server, Machine Learning Operations, TensorRT, Drift Detection, C++14, Software Version Control, Docker
- **Published:** November 6, 2026
- **Apply:** https://www.adzuna.es/details/5954152081

## About the Role

* Custom TensorRT plugins.
 * Industrial cameras - GigE Vision (ideally Basler pylon); optics, lighting and photometric calibration (flat-field).
 * Anomalib (advanced use or upstream contributions).
 * Manufacturing / quality context (automotive or another regulated industry); ISA-95 and IEC 62443.
 * Public cloud and cloud MLOps (ideally Azure: IoT Edge, ML).
 * Publications, talks or open source in vision / anomaly detection.

## Description

* Expert-level PyTorch: CNN / transformer vision architectures, training, evaluation and rigorous ONNX export (zero train/serve skew).
 * One-class / unsupervised anomaly detection: PatchCore, EfficientAD, PaDiM, student-teacher, normalizing flows, and their real failure modes (reference-set contamination, threshold calibration with few or no defective samples, synthetic defects via cut-paste / DRAEM, over-rejection, drift).
 * Supervised defect segmentation and detection (encoder-decoder, DETR-family): training, acceptance criteria and imbalanced datasets.
 * Methodological rigor: AUROC / AUPRO alongside plant-level metrics (escape rate, false-reject rate) and regression validation against recorded data.

C++ & Real-Time Systems

 * Expert-level modern C++ (C++17/20) for real-time vision pipelines, in addition to expert Python.
 * High-performance systems design: native pipeline/orchestrator coordinating capture, pre-processing, inference and post-processing while keeping data in memory and avoiding unnecessary copies and hops.
 * Hard latency budgets: determinism, watchdogs and graceful degradation.
 * Linux, Docker, Git and CI as the natural working environment.

GPU & Inference Optimization (NVIDIA)

 * Solid CUDA: execution model, streams, CUDA Graphs, memory management (pinned, unified, pre-allocation), writing and debugging custom kernels.
 * GPU libraries: cuBLAS, NPP, CV-CUDA, Thrust or equivalents for accelerated image pre-processing and scoring.
 * TensorRT in production: engine building, mixed FP16 / INT8 precision with custom quantization calibration, precision-degradation diagnosis and dynamic batching.
 * Triton Inference Server in production.
 * Profiling with Nsight Systems / Nsight Compute; p99 latency characterization per stage and finding the real bottleneck before optimizing.

Data & MLOps

 * Model versioning and registry (MLflow or equivalent), reproducibility and dataset curation (CVAT).
 * Traceability: able to demonstrate which model, data and version produced a given result.
 * Models in production: monitoring, drift detection and a retraining / rollback policy.