We are looking for a talented and passionate **Data Scientist** to join our team in Bahrain. As our Data Scientist, you will be responsible for the entire data lifecycle that powers our platform. You won't just analyze data—you'll be actively acquiring, cleaning, and structuring it. Your mission is to transform the web's messy, unstructured automotive data into a pristine, highly\-stratified database. Your work will directly fuel our platform's core competitive advantage: a powerful, intuitive, and accurate search feature that allows users to find the exact car or part they need, every time. **Key Responsibilities** * **Data Acquisition:** Design, build, and maintain robust web scraping pipelines to collect vast amounts of data on vehicles, parts, prices, and specifications from diverse online sources. * **Data Pipelines:** Build and manage robust data pipelines for search, model training, validation and inference, ensuring data integrity and efficiency. * **Data Stratification \& ETL:** This is the core of the role. Develop and implement advanced data cleaning, normalization, and standardization processes. You will: * Handle and parse messy, unstructured text data. * Resolve inconsistencies, deduplicate entries, and impute missing values. * **Stratify** data by creating clear taxonomies and hierarchies (e.g., categorize parts by make, model, year, system, and compatibility). * **Database \& Search Engineering:** * Work closely with the engineering team to design the database schemas (SQL or NoSQL) needed to store this complex, structured data. * Engineer and structure data specifically to power a high\-performance search engine (like Elasticsearch). * Define the relationships between data points (e.g., which part fits which car model). * **Analysis \& Insights:** Analyze the collected data to identify market trends, pricing insights, and gaps in our data inventory to guide future scraping and product strategies. * **Quality Assurance:** Continuously monitor the health of data pipelines and the quality/accuracy of the data, implementing automated checks and alerts. **Required Skills \& Qualifications** * **Experience:** 2\-4\+ years of hands\-on experience in a data\-heavy role (e.g., Data Scientist, Data Engineer). Startup experience is a major plus. * **Core Tech:** * Strong proficiency in **Python** and its data science/engineering ecosystem (Pandas, NumPy). * Proven, extensive experience with web scraping libraries and frameworks (Scrapy, BeautifulSoup, Playwright) * Good knowledge of TensorFlow, PyTorch, or scikit\-learn. * **Data Handling:** * Expert\-level data cleaning and manipulation skills. You must be comfortable wrangling messy, real\-world data. * Solid understanding of database technologies, both SQL and search\-oriented NoSQL.(Postgres, MySQL) **Preferred (Bonus) Qualifications** * **Passion for cars!** A strong interest in or knowledge of the automotive industry, vehicle specifications, and car parts is a huge advantage. * Hands\-on experience building and tuning search algorithms using **Elasticsearch**. * Experience with NLP (Natural Language Processing) for extracting structured information from text descriptions. * Familiarity with cloud platforms (AWS, GCP, or Azure) and data pipeline orchestration tools (e.g., Airflow). **What We Offer** * A competitive salary and benefits package. * The opportunity to work on challenging and impactful AI projects. * A collaborative and innovative work environment. * Support for continuous learning and professional growth. * The chance to be a key player in shaping the future of AI. Job Types: Full\-time, Permanent Ability to commute/relocate: * Manama: Reliably commute or planning to relocate before starting work (Preferred) Location: * Manama (Required)