Data Scientist

About VOX

VOX is a visionary company led by a single founder, currently leading the way in flashcall and telecom carrier services, transforming the way businesses communicate, authenticate and connect. As a hyper-growth company, VOX achieved over 25% YoY revenue growth last year and is aiming to reach $100M+ revenue this year. VOX is looking for a team of growth-driven individuals to take the company to new heights.

VOX's cutting-edge technology and dedicated customer service team ensure that telcos and enterprises maintain secure, fast, and reliable connections while protecting their networks. VOX's promise of a hassle-free experience and superior customer support enables telcos and enterprises to focus on success. As a company, VOX focuses on solutions that monetize the assets of mobile network operators. 

Joining VOX offers the opportunity to work with the industry's leading technologies and help them stay ahead and continue to innovate with a comprehensive suite of flashcall and telecom carrier services. VOX is highly committed to providing its employees with a dynamic, forward-thinking work environment, competitive compensation and benefits, vacation and time-off packages, and stock options. This is a once-in-a-lifetime opportunity for highly ambitious individuals, as VOX plans to expand its solutions portfolio and go public in the next 3-5 years.

About the Role

VOX is building a multi-tenant Customer Data Platform for mobile network operators across multiple countries. Our platform ingests billions of telecom events and transforms them into actionable insights, segmentation, scoring, and campaign activation.

As a Data Scientist on the VOX CDP team, you will work across Spark-based large-scale analytics, telecom event modeling, classification and clustering, scoring systems, and audience intelligence features. You will leverage Iceberg/Nessie datasets and collaborate closely with Data Engineers and Product to build models that power user segmentation, sender profiling, and activation use cases.

This is a role for someone excited by massive event data, ML at scale, and advanced behavioral modelling.

Responsibilities

Exploratory & Descriptive Analytics (Spark + Dremio)

• Analyze high-volume telecom datasets
  
• Build large-scale EDA workflows using Spark (batch + distributed analytics)
  
• Use Dremio to explore, validate, and aggregate Iceberg data efficiently
  
• Produce actionable insights on user behavior, engagement, messaging patterns, and campaign outcomes
  
  

 Feature Engineering & Data Modeling (Python + Spark)

• Develop scalable feature sets for:
  Relevance scoring
  Sender categorization
  Engagement propensity
  Audience quality/quantity modelling
  Cohort analysis
  
  
• Build reusable transformation pipelines on Spark that integrate directly into Iceberg tables
  
• Work with Data Engineers to deploy feature pipelines into production environments
  
  

ML Model Development (Classification, Clustering, Scoring)

• Build models for telecom-specific use cases, including:
  
  Category prediction for senders
  RFU scoring refinement
  User-level behavioral segmentation
  Anomaly detection on message activity
  Propensity and engagement ML models
  
  
• Select and implement appropriate ML techniques (tree-based models, embedding, clustering, graph-based grouping, etc.)
  
• Evaluate model performance with robust offline validation strategies
  
  

Campaign & Audience Intelligence

• Develop analytical models for campaign performance:
  Response modelling
  Lift analysis
  Control vs. exposed cohort evaluation
  Confidence intervals and campaign impact scoring
  
  
• Build audience scoring and relevancy models used directly in VOX's segmentation engine
  
• Work with product teams to define intelligence features that help MNOs select the strongest audiences
  
  

Model Deployment & Operationalize (CI/CD + Kubernetes)

• Package models and feature pipelines for deployment in multi-tenant MNO clusters
  
• Version and manage model releases via Git-based CI/CD
  
• Ensure reliable execution of batch scoring jobs on Kubernetes/Spark
  
• Monitor model health, drift, and performance across multiple deployments
  
  

Experimentation & Validation

• Design and evaluate experiments (A/B, multivariate, holdout cohorts)
• Build frameworks for causal measurement in messaging and telecom campaigns.
• Validate assumptions using statistical tests and robust confidence intervals.
  
  

Collaboration & Product Development

• Work closely with Data Engineers to ensure features and models are aligned with Iceberg/Nessie patterns
• Collaborate with Product to define new intelligence features in the VOX CDP
  
• Support customer-facing teams with insights, findings, and data stories
  
• Ensure models respect all PII and compliance rules across multi-tenant deployments.
  
  

Requirements

• 3+ years of experience as a Data Scientist, ML Engineer, or similar role
  
• Strong Python skills (must-have) for modeling, feature engineering, and data analysis
  
• Experience working with distributed analytics using Spark
  
• Strong SQL skills and comfort working with Iceberg datasets via engines like Dremio or Trino
  
• Solid background in machine learning (classification, clustering, time-series, scoring)
  
• Experience with model deployment, versioning, and CI/CD workflows
  
• Familiarity with building data products on top of large event datasets
  
• Understanding of PII handling, compliance requirements, and secure data processing
  
• Ability to work in multi-environment, multi-deployment contexts (dev/test/prod + multiple MNOs)

Nice to Have

• Experience with telecom datasets
  
• Knowledge of audience-building, relevancy scoring, or marketing activation models
  
• Experience with ML observe-ability (drift monitoring, model health checks)
  
• Understanding of Nessie branching workflows and Iceberg snapshot logic

Join the team and help shape the future of the telecom industry

We collect and process your personal data solely for recruitment purposes. Your data will be handled with the utmost care and in compliance with applicable data protection laws. For a detailed understanding of your rights, please refer to the Privacy Notice Regarding The Processing Of Personal Data In The Recruitment Process, available on our website
here.