Senior Data Scientist

i2c Inc; Lahore; On-site; PKR 2,000,000 - 3,000,000; Full time

Job summary

i2c Inc is seeking a Data Science Lead in Lahore to oversee end-to-end models in fraud detection. You will lead a team of data scientists, driving feature discovery to minimize fraud and foster model improvements.

The ideal candidate has 6-10 years of experience in data science, proficient in Python and SQL, with a track record in deploying models. Additional skills in Docker and Kubernetes are advantageous. This role is critical in ensuring effective communication across teams.

Qualifications

• 6 – 10 years of applied data science / ML experience, including models shipped to production.
• Expert in Python (pandas, numpy, scikit-learn) and strong SQL for extraction, aggregation, and complex analysis.
• Proven experience deploying and monitoring models in production.

Responsibilities

• Own models end-to-end across the fraud suite.
• Lead a team of 5–10 data scientists and engineers.
• Investigate client case studies and root-cause issues in the pipeline.

Skills

Python

SQL

Supervised ML

Leadership and mentoring

Data deployment and monitoring

Tools

Docker

Kubernetes

Spark

Airflow

Job description

• Own models end-to-end across the fraud suite - transaction fraud detection, 3DS friction reduction, enrolment fraud, merchant fraud, cardholder risk scoring, and NLP/LLM-based products - from design through production deployment and monitoring.
• Lead a team of 5–10 data scientists and engineers: set technical direction, review work, mentor junior members, and uphold engineering and modelling standards.
• Drive feature discovery through deep EDA - form strong hypotheses, test them rigorously, and translate findings into production features that measurably reduce fraud and false declines.
• Investigate client case studies: when banks report missed fraud or declines of genuine transactions, root-cause the issue in our pipeline, quantify impact, and propose model or feature fixes.
• Build robust data pipelines and experiments using Python, complex SQL, and distributed/orchestration tooling.
• Communicate with impact - present results and trade-offs to product, engineering, management, and clients; resolve conflicts within and across teams.
• Ensure ML best practices: version control, reproducible workflows, automated testing for data/model code, and post-deployment monitoring.

We are looking for

• Experience: 6 - 10 years of applied data science / ML experience, including models shipped to production.

Skills

• Expert in Python (pandas, numpy, scikit-learn) and strong SQL for extraction, aggregation, and complex analysis.
• Solid grounding in supervised ML and model evaluation (imbalanced classification, calibration, feature importance/interpretability).
• Proven experience deploying and monitoring models in production.
• Demonstrated leadership / mentoring of a 5–10 person team and the ability to resolve team-level conflicts.
• Clear communicator able to bridge technical depth and business stakeholders.

Nice-to-have (bonus)

• XGBoost and other gradient-boosting / deep learning frameworks.
• Exposure to LLMs, RAG, and Agentic AI workflows.
• NLP experience (e.g., scoring CSR call quality, conversational agents).
• Domain experience in payments, fraud, or risk - authorizations, 3DS, chargebacks, issuer processing.
• Experience with Data Engineering and MLOps tools (like Docker/Kubernetes, Spark, Airflow), Git, and visualization tools (matplotlib/plotly).