Назад
Company hidden
2 дня назад

Senior Applied Scientist (Computer Vision)

Π€ΠΎΡ€ΠΌΠ°Ρ‚ Ρ€Π°Π±ΠΎΡ‚Ρ‹
hybrid
Π’ΠΈΠΏ Ρ€Π°Π±ΠΎΡ‚Ρ‹
fulltime
Π“Ρ€Π΅ΠΉΠ΄
senior
Английский
b2
Π‘Ρ‚Ρ€Π°Π½Π°
Netherlands
Вакансия ΠΈΠ· списка Hirify.GlobalВакансия ΠΈΠ· Hirify Global, списка ΠΌΠ΅ΠΆΠ΄ΡƒΠ½Π°Ρ€ΠΎΠ΄Π½Ρ‹Ρ… tech-ΠΊΠΎΠΌΠΏΠ°Π½ΠΈΠΉ
Для мэтча ΠΈ ΠΎΡ‚ΠΊΠ»ΠΈΠΊΠ° Π½ΡƒΠΆΠ΅Π½ Plus

ΠœΡΡ‚Ρ‡ & Π‘ΠΎΠΏΡ€ΠΎΠ²ΠΎΠ΄

Для мэтча с этой вакансиСй Π½ΡƒΠΆΠ΅Π½ Plus

ОписаниС вакансии

ВСкст:
/
TL;DR
Senior Applied Scientist (Computer Vision): Developing algorithms and machine-learning solutions that detect, position, and connect traffic-control features to roads and driving directions with an accent on computer vision, geospatial geometry, and large-scale noisy data. Focus on productionizing ML pipelines, improving recall and precision, and solving complex map-matching and evaluation challenges.

Location: Amsterdam, The Netherlands; hybrid work with two office days per week. Candidates must already live in the Netherlands; relocation is not offered.

Company

hirify.global develops real-time maps and location technology for car manufacturers, enterprises, developers, and navigation users.

What you will do

  • Develop algorithms and ML solutions for traffic signs, traffic lights, road markings, and other traffic-control features using computer vision and image recognition.
  • Design and productionize solutions that extract map information from large-scale, noisy car-sensor and unstructured data.
  • Improve feature detection, positioning, road and lane association, and driving-direction matching.
  • Drive measurable improvements in recall, precision, and customer-facing map quality.
  • Own production pipeline components from input data and feature extraction through evaluation and validated map output.
  • Run experiments, document results, use AI tools for problem solving and implementation, mentor junior colleagues, review code, and contribute to hiring.

Requirements

  • 4+ years of professional experience in applied science, machine learning, algorithm development, computer vision, or a related field.
  • Bachelor’s degree or higher in computer science, machine learning, computer vision, geospatial science, statistics, or another quantitative field.
  • Strong fundamentals in algorithms and machine learning, including model development, evaluation, statistics, and experimental design.
  • Proficiency in Python, an ML framework such as PyTorch or TensorFlow, and large-scale data processing tools such as Spark or Databricks.
  • Experience moving algorithms, ML models, or data pipelines from experimentation into production.
  • Experience leading well-scoped technical projects and mentoring junior colleagues.
  • Ability to work across data, algorithms, modeling, ground truth, and evaluation rather than only one area of expertise.
  • Strong problem-solving skills and ability to independently approach complex and ambiguous problems.
  • Proficient written and verbal English communication skills.
  • Already living in the Netherlands; relocation is not available for this role.

Nice to have

  • Master’s degree or PhD.

Culture & Benefits

  • Hybrid work using both the office and home, with three additional working days available from either location.
  • Personal development budget, paid learning days, and access to O’Reilly and LinkedIn Learning.
  • Enhanced parental leave, paid leave to care for loved ones, and paid volunteering leave.
  • Home-office setup budget and monthly allowance.
  • Options to work from the home country or abroad for a set number of days each year.
  • Competitive holiday plan, birthday leave, annual hackathon and DevDays, and an inclusive international culture with over 80 nationalities.

Hiring process

  • Applications are screened, followed by assessments and interviews before onboarding.

Π‘ΡƒΠ΄ΡŒΡ‚Π΅ остороТны

Если Ρ€Π°Π±ΠΎΡ‚ΠΎΠ΄Π°Ρ‚Π΅Π»ΡŒ просит Π²ΠΎΠΉΡ‚ΠΈ Π² ΠΈΡ… систСму, ΠΈΡΠΏΠΎΠ»ΡŒΠ·ΡƒΡ iCloud/Google, ΠΏΡ€ΠΈΡΠ»Π°Ρ‚ΡŒ ΠΊΠΎΠ΄/ΠΏΠ°Ρ€ΠΎΠ»ΡŒ, Π·Π°ΠΏΡƒΡΡ‚ΠΈΡ‚ΡŒ ΠΊΠΎΠ΄/ПО, Π½Π΅ Π΄Π΅Π»Π°ΠΉΡ‚Π΅ этого. Π­Ρ‚ΠΎ мошСнники. ΠžΠ±ΡΠ·Π°Ρ‚Π΅Π»ΡŒΠ½ΠΎ ΠΆΠΌΠΈΡ‚Π΅ Β«ΠŸΠΎΠΆΠ°Π»ΠΎΠ²Π°Ρ‚ΡŒΡΡΒ» ΠΈΠ»ΠΈ ΠΏΠΈΡˆΠΈΡ‚Π΅ Π² ΠΏΠΎΠ΄Π΄Π΅Ρ€ΠΆΠΊΡƒ. ΠŸΠΎΠ΄Ρ€ΠΎΠ±Π½Π΅Π΅ Π² Π³Π°ΠΉΠ΄Π΅ β†’