Lead Data Scientist

We are looking for a hands-on Lead Data Scientist with strong analytical, machine learning, and problem-solving skills to work in a client-facing environment.

The role requires someone who can independently identify opportunities, formulate hypotheses, design solutions, and drive initiatives from analysis through experimentation and production implementation. The candidate should also be comfortable guiding team members and working closely with engineering and client stakeholders.

Responsibilities

Analyse complex datasets to identify patterns, issues, and opportunities.

Formulate and validate hypotheses through structured analysis and experimentation.

Build and improve machine learning and anomaly detection solutions.

Design end-to-end solutions considering data, modelling, engineering, and production constraints.

Perform root cause analysis across models, data, and systems.

Work with engineering teams on feature pipelines, model inference, and production deployment.

Lead technical discussions with clients and communicate recommendations, trade-offs, and expected impact.

Guide team members on analysis, modelling, and solution design.

Proactively identify initiatives and roadmap items that can add value to the project.

Requirements

Strong foundation in statistics and machine learning.

Strong hands-on experience with Python and SQL.

Hands-on experience with Python ML and data frameworks such as Pandas, NumPy, scikit-learn, TensorFlow/Keras, Dask, Matplotlib, Boto3 SageMaker Python SDK, and Horovod.

Strong data analysis, hypothesis-generation, and problem-solving skills.

Experience with standard supervised and unsupervised ML techniques.

Experience with anomaly detection techniques such as Isolation Forest and Autoencoders.

Experience building and deploying production ML solutions.

Working knowledge of data engineering and real-time / batch inference environments.

Strong communication and stakeholder-management skills.

Ability to lead technical work and guide cross-functional teams.

Good to Have

Experience in fraud detection or risk modelling.

Experience with Graph Neural Networks.

Exposure to real-time systems, streaming features, and low-latency data stores.

Experience in AdTech, e-commerce, gaming, mobile applications, or similar high-volume consumer platforms.