DANIEL AZEMAR
Computer Vision & Software Engineer — Real-Time Systems · AI · Agentic Workflows
Barcelona, Spain

dani@azemar.eu · https://azemar.eu/cv
LinkedIn: https://www.linkedin.com/in/daniel-azemar-45772413b/
GitHub: https://github.com/dazca
StackOverflow: https://stackoverflow.com/users/5102670/daniel-azemar

Concise public version — described by work and stack rather than employer
name, by choice. Full detail on request: dani@azemar.eu
Machine-readable profile for AI agents: https://azemar.eu/llms.txt


SUMMARY
-------
Engineer with ~8 years taking vision and sensing systems from research into
production under real physical constraints. Three converging tracks: production
computer vision at city scale (30+ edge-AI camera networks, 300+ TB of imagery),
real-time embedded firmware, and scientific data pipelines (ESA Euclid ground
segment). Currently working hands-on in computer vision. MSc in Computer
Vision, UAB.

Roles below are described by the work and the stack rather than by employer
name. Employer detail and references on request.


PROFESSIONAL EXPERIENCE
-----------------------

2026 – present · Computer Vision Engineering
Video analytics for perimeter security and environmental monitoring

  - Detection and tracking models for a product where inference runs on
    constrained hardware in the field, not in a datacentre.
  - Returning to hands-on computer vision with four years of embedded and
    real-time systems work added underneath it.

2022 – 2026 · R&D Software Engineering
Industrial embedded systems

  - Firmware in C/C++ for embedded microcontrollers (low-level, real-time),
    with latency as a key design driver.
  - SQL/NoSQL database design for hardware-software data integration,
    improving query efficiency.
  - Real-time systems and algorithm optimisation: threading, schedulers,
    latency-critical workloads.
  - Cross-platform C#/.NET server infrastructure.

2018 – 2022 · Computer Vision & AI Engineering
Environmental monitoring and smart-city systems

  - Led projects end-to-end, from research to production deployment.
  - Real-time computer vision for traffic, safety and environmental
    monitoring: detection, tracking, image enhancement and classical
    processing pipelines.
  - Trained and fine-tuned a wide range of state-of-the-art vision
    architectures for detection and classification.
  - Deployed 30+ edge-AI camera networks processing 100k+ daily transactions;
    scalable pipelines over 300+ TB of self-built datasets; shared edge/cloud
    framework and monitoring GUIs.

2017 · Software Engineering (internship)
Scientific data centre — ESA Euclid Mission ground segment

  - Performance-sensitive validation tools improving accuracy and efficiency
    of astronomical data processing; data-integrity protocols under
    high-throughput conditions.


EDUCATION
---------

2020 – 2022 · UAB — Mathematics coursework
  Linear algebra, statistical modelling, optimisation, calculus.

2018 – 2020 · UAB — MSc in Computer Vision
  Thesis: "From haze to smoke: weakly-supervised smoke detection"
  PDF: https://azemar.eu/docs/msc-thesis-weakly-supervised-smoke-detection.pdf

2014 – 2018 · UAB — BSc in Computer Science
  Thesis: "Temporal resolution enhancement of multi-spectral image sequences"
  Repository: https://ddd.uab.cat/record/196902


SKILLS & EXPERTISE
------------------

Languages
  C/C++ (C++11/17, Linux/Windows), Python (NumPy, OpenCV, PyTorch), C#/.NET,
  SQL, MATLAB, JS/HTML/CSS, Bash, PowerShell.

AI / Machine learning
  Object detection & classification architectures, CNNs, transformers,
  PyTorch, TensorFlow, Keras, scikit-learn, ONNX, fine-tuning, pruning,
  few-shot learning, optical flow, data augmentation.

Data engineering
  SQL/NoSQL, ETL pipelines, large-scale dataset management, automated
  labelling, distributed training, Weights & Biases, NumPy, SciPy, Astropy.

Systems
  RTOS, microcontrollers, CUDA, edge GPUs, thread scheduling, latency tuning,
  board bring-up, hardware-software integration.

Infrastructure
  Git, Docker, CI/CD, Linux, Windows, Cloudflare Workers/Pages/KV/D1, LaTeX.

Agentic workflows
  AI-assisted engineering with agentic coding tools (Claude Code, Copilot,
  Codex) integrated into daily practice — from prototyping to production
  automation. Applied in the multi-site web estate at azemar.eu.


LANGUAGES
---------
Catalan — native
Spanish — native
English — professional working proficiency (B2, Cambridge First Certificate)


INTERESTS
---------
Astrophysics and physics · Board games · Mountain hiking · Snowboarding


Interactive version: https://azemar.eu/cv
Full CV with employer and technology detail: dani@azemar.eu
Last updated: 2026-09-16