Senior Data Scientist
Descrição da empresa
Farfetch is an innovative e-commerce company that brings the world's best fashion boutiques to an international audience. Launched in October 2008, Farfetch is rapidly growing into a truly global company. Our family now includes more than 1000 talented people and 400 independent boutiques across Europe, North and South America, Asia, and offices in London, New York, LA, Porto, Guimarães, São Paulo, Tokyo, Shanghai, Moscow and Hong Kong.
Descrição do cargo
Farfetch is building the next-generation intelligent platform for online luxury fashion, powered by large-scale data and state of the art Machine Learning, Deep Learning and Computer Vision algorithms. You will join a talented team of Data Scientists, Engineers and Product designers to help build and optimize, through research and experimentation, our data-driven products.
What you will do
- Design and develop state of the art algorithms in one of these domains: Ranking, Natural Language Processing or Computer Vision;
- Conduct practical research with a scientific mindset, and a focus on delivery;
- Build large scale data pipelines;
- Work closely with the engineering team to integrate ML algorithms into the platform;
- Help in the design of new features in the product, and drive innovation inside the company through the use of disruptive technologies.
Who you are
- MSc or PhD in related topics such as Machine Learning, Natural Language Processing, Computer Vision, Signal Processing, Speech Processing or Optimization;
- We encourage applications also with background from the fields in Computer Science, Electrical Engineering, Physics, Biomedical Engineering, Statistics, Applied Mathematics;
- Knowledge in one of the following subjects:
- Word Embeddings (e.g., GloVe, Word2Vec), Named Entity Recognition models;
- Information Retrieval, Learning to Rank (e.g., RankNet, ListNet), algorithm performance metrics (e.g., NDCG);
- Convolutional Neural Networks (e.g., InceptionV3, RetinaNet), Image Segmentation (e.g., SLIC, Saliency Maps, SuperVoxel), AutoEncoders, GANs;
- Fluent in Python and common numerical and Math & ML packages (NumPy, SciPy, sci-kit-learn, pandas, Keras, TensorFlow, PyTorch). R candidates are also encouraged to apply;
- Experience dealing with large amounts of data and building data pipelines;
- Knowledge of big data technologies is a plus (Hadoop, Spark, Hive);
- Non-relational databases (e.g., Cassandra) and streaming platforms know-how (e.g., Kafka) is a plus;
- Strong English skills, both written and spoken;
- Scientific and technical publications are possible and encouraged; Applicant should be interested to keep up to date with scientific advancements.