About Vortexa
Vortexa was established to address the significant information gap in the energy sector. Using an extensive amount of satellite data and innovative work in artificial intelligence, Vortexa offers an unmatched viewpoint on the global seaborne energy flows in real-time, bringing clarity and efficiency to energy markets and society at large.
The Challenge
Processing thousands of data points per second from a variety of different external sources, maneuvering terabytes of data while processing it in real time, operating complex prediction and forecasting AI models and incorporating their output into a blended human-machine data improvement process, and presenting the result through a nimble low-latency SaaS solution utilized by global customers is a significant feat of science and engineering. This processing calls for models that can stand up to the examination of industry experts, data analysts, and traders, with the performance, stability, latency, and agility required by a rapidly evolving startup impacting multi-million dollar transactions.
The Data Production Team handles all of Vortexa's data, ranging from blending raw satellite data from 600,000 vessels with rich but incomplete text data, to producing valuable predictions such as vessel destination, cargo onboard, ship-to-ship transfer detection, dark vessels, congestion, future prices, and so on. The team uses a variety of procedural, statistical, and machine learning models to offer the most precise and comprehensive view of energy flow. Our data quality is constantly evaluated and verified by internal market and data analysts to ascertain the accuracy of our predictions.
You will be crucial in the design and construction of infrastructure and applications to advance the design, deployment, and benchmarking of existing and new pipelines and ML models. Alongside software and data engineers, data scientists and market analysts, you will assist in bridging the gap between scientific experiments and commercial products, ensuring 100% uptime and fault tolerance of every aspect of the team's data pipelines.
Learning Opportunities
You will be seen as an essential member of a team of 3-5 engineers and data scientists, and will assist in achieving the same objectives and roadmap as your colleagues. By working on common projects, you will receive immediate and thorough support and feedback, which, we believe, is the best way to enhance your learning and impact.
Our aim is to identify and develop promising talents. It serves our interests to aid you in succeeding. If there's a fit, you'll be the first option for hiring. The role provides the chance to help with and lead projects in data engineering, machine learning, and business.
You will use key technologies like Python, SQL, Rust, Java, Kotlin, AWS, Docker, Kubernetes, Airflow, Kafka, S3, and Postgres. For assignments longer than 6 months, you may be given the opportunity to switch teams mid-placement.
Requirements
Applicants must be proficient in software engineering fundamentals, driven by working in an intellectually stimulating environment with some of the industry's brightest minds, eager to work in a startup environment, fluent in Python, and comfortable with Pandas/Numpy.
Benefits
Benefits include a dynamic, diverse company pushing the boundaries of technology, a team of motivated individuals striving for excellence, constant learning and exploration of new tools and technologies, working and achieving together, a flexible working policy accommodating both remote & home working, private health insurance, a global volunteering policy, and equity options for all Vortexa staff.