Factmata's mission is to allow anyone to discern and verify the credibility, quality, safety and reliability of online content. We are building state-of-the-art technology to semi-automatically score and verify news and social media using a combination of an expert network platform for machine learning, and advanced natural language understanding techniques. Our team consists of top researchers in NLP and machine learning, and we are backed by the founder of Twitter, Craigslist, Zynga and Broadcast.com.
We are looking for a machine learning engineer to join the team and build algorithms for quality scoring and text classification. This role is a practical machine learning role with a component of research, but focused on building data products for our clients, for example brands, PR agencies, platforms and advertising partners.
What you'll be doing
Driving small iterative experiments around new ideas, datasets and partner integrations
Measuring and improving the quality of the algorithms
Working closely with client requirements to make sure we deliver a high-quality solution
Building NLP pipelines and models, which range from linear models to state-of-the-art neural networks
Work with the platform team to integrate the models in production
Keeping up-to-date with research in the areas of misinformation NLP processing and always being on the look-out for new datasets
Who we're looking for
You feel strongly about the problem of misinformation and want to help us fight it
BSc or higher in computer science, related STEM or quantitative field
At least 2 year experience with applied machine learning & statistical natural language processing
Strong proficiency in Python and the python data ecosystem including Numpy, Pandas, Scikit-learn.
Proficiency in SQL
Curiosity about new developments in AI and machine learning
Excellent problem solving, critical thinking, creativity, organizational, design, and communication skills; ability to interact with all levels of engineers
Excellent knowledge of numerical optimisation techniques, statistics, ML algorithms and neural network architectures (CNNs, LSTMs, GANs).
Strong background in Linear Algebra, Statistics and Numerical Mathematics
You have a product-oriented mindset and like to work in an agile framework designing, conduction, analysing and interpreting experiments and investigations
You have industry experience in building machine learning into production systems
You have web mining and information retrieval experience
You have worked in content scoring, media scoring, sentiment analysis, and in more complex tasks related to information retrieval from news and knowledge bases
Familiarity exposing ML components through web services or wrappers (e.g. Flask)
Experience handling large datasets (>billions of rows)
Knowledge on scaling up computations (Spark, GPUs, MPI)
Familiarity with cloud environments (AWS, GCP, Azure)