Sigma Software Group
Sigma Software Group
1,001 – 5,000 Employees
AutomotiveConsultingHealthcare
Sigma Software Group is a multinational technology consulting company founded in 2002. Its teams provide software development, graphic design, testing, and technical support for clients in sectors including automotive, healthcare, telecommunications, aviation, banking, gaming, real estate, and advertising. The company hires IT specialists to work on complex engineering projects and supports professional development through mentoring and continuous learning. Remote work opportunities are part of its working model, with projects serving organizations such as AstraZeneca, Scania, and SAS.

Senior Data Scientist – Programmatic Advertising (Remote, Germany/Poland)

Build real-time machine learning and optimization systems for programmatic advertising. Develop predictive models for bidding, audience targeting, conversions, calibration, and campaign performance.

Description

  • Develop censored bid-landscape models to estimate clearing-price distributions from partially observed auction data
  • Create real-time win-probability models that adapt to bid-pricing dynamics
  • Design hierarchical lift-estimation models with confidence-bound selection strategies
  • Build conversion-propensity models from sparse, delayed, and aggregate-only labels
  • Develop look-alike audience models using positive-unlabeled learning and embedding-based nearest-neighbor methods
  • Implement advertiser-level calibration strategies and independently assess ranking and calibration quality
  • Design offline evaluation frameworks using inverse-propensity scoring, doubly robust estimators, and importance reweighting
  • Define exploration strategies and propensity-logging methods to support reliable correction and evaluation
  • Develop constrained optimization methods for campaign objectives, pricing limits, and volume targeting
  • Support data diagnostics, capability assessments, and evidence-based model recommendations
  • Work with the Customer team on post-launch tuning and performance validation
  • Prepare technical documentation and knowledge-transfer materials for the Customer’s internal data science team
  • Contribute to architecture discussions and scalable machine learning platform decisions

Requirements

  • At least five years of Machine Learning or Data Science experience delivering production models measured against business KPIs
  • Advanced Python skills, including NumPy, pandas, and scikit-learn
  • Strong SQL skills and experience handling large-scale datasets
  • Practical expertise with XGBoost, LightGBM, or CatBoost
  • Solid knowledge of regularization, calibration techniques, and categorical feature processing
  • Strong foundation in probability, statistics, confidence intervals, and statistical power analysis
  • Experience engineering features from structured and behavioral data
  • Hands-on experience with Spark or PySpark
  • Practical understanding of experimentation frameworks and A/B testing
  • Experience with advanced validation methods, including temporal splits, leakage detection, drift analysis, and slice-based metrics
  • Understanding of explainability methods such as SHAP and permutation importance
  • Upper-intermediate English proficiency or higher
  • Strong analytical and problem-solving abilities
  • Effectiveness in highly data-driven work environments
  • Strong communication and stakeholder-management skills
  • Ability to explain complex modeling decisions to technical and non-technical audiences
  • Proactive approach with a strong sense of ownership
  • High attention to detail and scientific rigor in experimentation and evaluation

Benefits

  • Remote work arrangement
  • Work on technically challenging products
  • Collaborate with experienced engineers and data scientists
  • Make a direct contribution to large-scale production systems

Related Jobs