Senior Data Scientist: Time Series and Logistics Optimization

Snoonu; Doha; On-site; QAR 250,000 - 350,000; Full time

Benefits offered by this job

Global Vibes

Brain Boosters

Builder’s Playground

Flexible Time Off

Agile Everything

Job summary

Snoonu is seeking a senior data scientist to lead time series forecasting and optimization efforts for its Doha-based logistics network. You will design, implement, and validate models that improve ETA, preparation times, and demand forecasting, while collaborating with ML engineers, backend teams, and product managers.

Responsibilities include experiments, robust benchmarking, and deploying retrainable pipelines.

Qualifications

• Advanced degree in data science, statistics, maths, CS, or related field.
• 5+ years in data science / ML with time series or optimization focus.
• Hands-on time series methods: ARIMA, Prophet, TFT, DeepAR, N-BEATS.
• Experience with optimization solvers (LP, MILP, OR-Tools, PuLP).
• Proficiency in Python data stack (Pandas, NumPy, Scikit-learn).
• Experience deploying ML models at scale and monitoring retraining pipelines.

Responsibilities

• Lead R&D for forecasting and optimization models.
• Design experiments, benchmarks, and robustness testing.
• Develop production ML pipelines with monitoring and retraining.
• Collaborate with ML, backend, researchers, and product teams.
• Drive A/B testing and quantify impact on logistics KPIs.
• Mentor junior engineers and promote best practices in modeling and coding.

Skills

Time series forecasting

Optimization methods

Python data stack

A/B testing

Big data / SQL

Cloud ML deployment

Education

MSc in Data Science / related

PhD (nice to have)

Tools

OR-Tools

PuLP

TensorFlow / PyTorch

LightGBM

BigQuery

Job description

Snoonu is seeking a senior data scientist to lead time series forecasting and optimization efforts for its Doha-based logistics network. You will design, implement, and validate models that improve ETA, preparation times, and demand forecasting, while collaborating with ML engineers, backend teams, and product managers.

Responsibilities include experiments, robust benchmarking, and deploying retrainable pipelines.