xgo - Data Scence Engneer - Artfcal Intellgence/Machne Learnng

Job Description :

We are looking for a Data Science Engineer / Senior Research Engineer to join our applied AI team at Abhibus. This is a hybrid role at the intersection of AI/ML, classical data science, and data engineering.

You'll be responsible for :

- Designing and building AI-driven features that power search, personalization, pricing, recommendations, and fraud detection.

- Developing robust data pipelines and scalable infrastructure to ensure reliable ML model training and deployment.

- Generating statistical and business insights from large-scale bus travel data to shape product strategy.

- Your work will touch millions of travellers and hundreds of bus operators, bringing datadriven innovation to the mobility ecosystem.

Key Responsibilities :

- Design and implement ML models for personalization, demand forecasting, route optimization, pricing, anomaly detection, and recommendations.

- Build, maintain, and optimize ETL/data pipelines to feed ML models and analytics dashboards.

- Work with product managers & engineers to translate business requirements - models - production systems.

- Perform statistical analysis, A/B testing, and causal inference for product & growth experiments.

- Read and adapt academic research papers into practical product applications.

- Ensure model lifecycle management : data collection, feature engineering, training, deployment, monitoring, and retraining.

- Collaborate with data engineering team on data architecture, warehousing, and scaling pipelines.

Qualifications :

- Background in Computer Science, Engineering, or Mathematics (top institutes preferred).

- 2-6 years of experience in data science & engineering.

- Strong fundamentals in algorithms, data structures, ML/DL, and statistics.

- Proficiency in Python and libraries like TensorFlow/PyTorch, Scikit-learn, Pandas, NumPy, SciPy.

- Hands-on experience with SQL and data pipelines (Airflow, Spark, Kafka, dbt, or equivalent).

- Ability to translate ambiguous problems into structured models and scalable solutions.

Preferred Skills :

- Experience with cloud platforms (AWS, GCP, Azure) and ML deployment tools (SageMaker, MLflow, Kubeflow).

- Knowledge of big data technologies (Spark, Hadoop, Presto, ClickHouse).

- Experience with travel, mobility, or marketplace problems.

- Contributions to open-source ML or published research.