Senior Data Scientist

Senior Data Scientist at Truecaller, building machine-learning systems for caller identity, business identification, spam and fraud detection.

  • Stockholm
  • På plats
  • Interim consultant

Om uppdraget

The Trust Intelligence & Calling team builds the machine-learning systems behind Truecaller's core promise: telling people who is calling and whether they can trust them. The team picks the name shown for every number, identifies businesses, and detects spam and fraud for hundreds of millions of users across very different markets. Signals are noisy and adversarial, and scammers and spammers adapt quickly. Remote candidates are also being considered.

Plats och erfarenhet

Plats
Sweden
Erfarenhetsnivå
Senior

Arbetsuppgifter

  • You lead the technical direction of key models in this area, and you set the practices that make model changes measurable and safe to ship.
  • Own models end to end across caller identity, business identification, spam and fraud detection: problem framing, data, training, evaluation, deployment and monitoring.
  • Work on a mix of ranking, classification, graph, personalisation and LLM-based models, together with the engineers who serve them at scale.
  • Set the evaluation standard for the team. That means backtests on historical data, honest baselines, false-positive checks on legitimate callers, shadow runs, and A/B tests.
  • Build shared tooling so good practice is the easy path: reusable evaluation harnesses, experiment tracking, project templates and moving work from notebooks into production code.
  • Work with product stakeholders to turn loosely defined problems into clear modelling goals and success metrics, and explain results and trade-offs to non-technical audiences.
  • Share model monitoring and incident handling, including drift detection.
  • Document decisions and results as short, reproducible analyses.

Krav

  • Several years of hands-on experience building and shipping machine-learning models to production.

Meriterande

  • Experience gathering requirements from non-technical stakeholders, turning them into a scoped plan, and communicating results and trade-offs clearly.
  • Experience setting or improving data science standards in a team (evaluation, reviews, reproducibility).

Obligatoriska kompetenser

  • Strong Python and SQL, and experience with large-scale data in BigQuery or a similar warehouse.
  • Experience with both classical ML (gradient boosting, ranking) and deep learning (TensorFlow/Keras or PyTorch), including training on GPUs.
  • Experience designing offline evaluations that predicted online results, and running A/B tests.
  • Experience working with pipelines in Airflow, dbt and Spark, or running training jobs on Kubernetes.

Meriterande kompetenser

  • Graph machine learning (GNNs, link prediction, label propagation) or recommendation and retrieval models (two-tower, embeddings).
  • Using LLMs in production for extraction, classification or generation, including LLM-as-judge evaluation.
  • MLOps tooling such as MLflow (or similar) for experiment tracking, model registry and versioning, and reproducible training.
  • NLP on short, multilingual or transliterated text such as names, or computer vision on user images.
  • Telecom or calling data, or experience in fraud detection.

Kvalifikationer

Språk

  • English
Minsta erfarenhet
5 år

Villkor och förmåner

Arbetstid
100%