Passion for large-scale real-time industrial data mining and dealing with massive rogue and coarse data.
Work with cross-functional stakeholders to understand the data needs of the company and ensure all new and existing product surfaces have the data they need to power the user experience, the business reporting, and the insights needed to drive further development.
Engage broadly with the organization to identify, prioritize, frame, and structure complex and ambiguous challenges, where advanced analytics projects or tools can have the biggest impact.
Translate business requirements into technical ones.
Define logging needs in partnership with Data Engineers.
Define the data science strategy for metrics and data models to ensure data is activated at scale.
Apply and combine current and emerging machine learning and data mining techniques and methods in novel ways for a specific application.
Architect, build, and launch efficient, reliable, robust, and scalable new data models and pipelines in partnership with software engineers and data engineers.
Evaluate the technical tradeoffs of every decision.
Create technical documentation for data models.
Create advanced reports and models by combining multiple data sources to help inform business decisions and strategies.
Transform real-world data into actionable insights using robust statistical methods and compelling data visualizations in formats accessible to a wide range of end-users.
Design and develop dashboards to enable self-serve data consumption.
Requirements:
Demonstrated skills in problem-solving and problem modeling (Strong knowledge of data structures and algorithm design is expected)
Ability to work with cross-functional stakeholders to perform Business Understanding.
Ability to deal with real-world massive industrial datasets and perform Exploratory Data Analysis.
Provable research skills (having a published research paper is a plus)
Proficiency in programming with Python (Familiarity with Java is a plus)
Deep knowledge of linear algebra and statistics.
Experience with classical machine learning techniques such as Naive Bayes, SVM, SVR, Logistic Regression, Decision Tree, Random Forest, K-Means, DBSCAN, etc, and tools such as scikit-learn.
Experience with representation learning, deep neural networks, and tools such as TensorFlow2 and Keras. (Familiarity with TF Datasets, TFX, and SpaCy is a plus)
Familiarity with large-scale and real-time machine learning applications such as Information Retrieval,Recommendation Systems, Anomaly Detection, Natural Language Processing, etc.
Fluency in querying languages such as SQL/KSQL.
Strong skills in distributed system optimization (e.g. Spark, Hadoop)
Experience with Data Viz techniques and tools such as Power BI, Tableau, D3.js, Kepler.gl, etc.
Experience with stream processing tools like Apache Kafka, Apache Flink, and Apache Beam is a plus.
Experience with an ETL framework like Airflow is a plus.
Experience with a cloud-native ML workflow platform such as Kubeflow is a plus.
معرفی شرکت
اسنپفود بزرگترین سرویس آنلاین سفارش غذا در ایرانه که در کنار غذا، سرویسهایی از جمله سفارش نان، پروتئین، شیرینی و میوه رو هم در خودش داره.
همراهی صمیمانه و اعتماد بیش از ۵ میلیون کاربر ما رو بر این داشته که همواره به دنبال خلق پدیدههای تازه و راهی برای خدمترسانی بهتر و باکیفیتتر باشیم.
ما در این مسیر علاقهمند به همکاری با افرادی هستیم که با هوشمندی و سرعت عملشون در عبور از چالشها و مسائل کسبوکار یاریگرمون باشن.