JOB DESCRIPTION
Trade with Pluto is searching for an experienced quantitative researcher to help them build high-frequency, low-latency stock trading techniques and models. Candidates will be a part of a team that will combine Trade with Pluto's considerable options experience with indications from the underlying stock market. Candidates will be responsible for doing large-scale data analysis in order to create distinctive equity market behavior predictions.
Candidates will join a growing team that will be critical to all elements of Trade with Pluto's operations after they are hired. They will not only help with signal generation, but also with the design and execution of a solid framework that will allow new ideas to be investigated, tested, and implemented in a timely manner.
KEY RESPONSIBILITIES
• Understand the current suite of models and algorithms with the aim to make any short-term improvements. While building a foundation to further leverage these models
• Find innovative ways to monetize existing algorithms through specific deep-dives and broad data analysis
• Rapidly research, test, and prototype new algorithmic ideas, preferably with Python
• Follow through with the high-quality implementation of concepts to full-scale production trading once they've been validated
SKILLS & EXPERIENCE REQUIREMENTS
• Working as an individual contributor for 5+ years as a python developer.
• Experience in developing large-scale Python programs from conception to execution, deployment, and testing.
• Clear understanding of the Python language's basics, as well as the ability to build both OO and functional code.
• Agile development method based on iteration with users, gathering feedback, and the ability to make code changes rapidly and confidently, all backed up by a good CI pipeline and test coverage.
• Application deployment and operating experience in the DevOps style: You should be able to stand behind your code, deploy it, and confirm that it satisfies the demands of your users.
• Experience with container orchestration approaches such as docker swarm, kubernetes, and cloud platforms, notably AWS, at scale on distributed systems. A strong advantage is familiarity with distributed analysis methodologies and platforms like Dask and PySpark.
