ML Engineer

About Us

Our mission is to build the first on-chain reputation protocol, allowing users to unlock benefits through their on-chain behaviour in DeFi. We achieve this through processing large amounts of data that gets scored through AI, ML, and data-driven applications before being uploaded to a user’s DeFi Passport. We have two products that we are building out with one product team for each product.

• DeFi Passport 💳: This is the product that allows users to access benefits on-chain through analysing their behaviour. We also allow 3rd party developers to use our infrastructure to create their own scores. This is a consumer facing team and about crafting a delightful product.
• ARCUSD 🏦: This is our credit scoring technology coupled with our loan issuance platform that allows users to borrow more through their borrowing behaviour. We focus on this since we believe that credit is the killer application of reputation. This team is primarily an infrastructure team and about robust engineering.

You’ll undoubtedly be wearing many hats while working alongside incredibly talented and driven individuals, fully remotely 🌏. We’ve raised over $8m till date from some of the industry’s top investors and are a team of 6 full time members and another 6 contractors/contributors/part-timers.

Values

Culture is extremely important to us and not just in a corporate-speak way. These are the things we pride ourselves on as a team:

• We love what we do and don’t view this as another job, rather an extension of their life’s work 🤗
• We are extremely good at what we do through demonstrated past experience and execution ability 🚀
• We care about the people around us and want to spend time developing and maintaining good relationships all around 😇

What we’re looking for

We are looking for ML Engineers to join our fledgling Data & ML team to help us create the awesome models that feed into our consumer facing products. You’ll have the opportunity to own the problem, and work on a series of greenfield initiatives that support our primary product offerings.

You should enjoy solving big, hairy, unstructured, and audacious goals while having the freedom to carve out your own path to a solution. You take a creative and critical approach to problems, challenging underlying assumptions and biases. You should be an expert in all things modelling and you aren’t afraid of getting your hands dirty to get your models into production. If you won’t settle for anything less than awesome, and thrive working with a team of uber-passionate engineers, then you’ll love working in our team.

You’d ideally have a strong mathematical or statistical grounding, and better still a depth of experience in actuarial studies. Crypto, blockchain, or DeFi experience is a huge plus. We primarily work with Python, Bash, Terraform, and GCP, and experience with these would be highly desired if not essential. We open to ramping you up on our problem domain and tech stack, given you have a demonstrated aptitude to learn quickly.

What you will be doing

• Working with a passionate team of Data & ML Engineers to solve novel and complex modelling challenges, most of which have never been attempted before in the DeFi space.
• Perform exploratory analyses on both open and proprietary data sources to provide rich, data-driven insights.
• Developing production-ready, cloud-centric data applications using a modern tech stack.
• Audit, interrogate, and monitor online systems to prevent model degradation and catch issues early.
• Have the ability to create a real impact, and meaningfully change the trajectory of our protocol.

What you should have

• +2 years working in a data science or analytics-centric role.
• +2 years writing, deploying, and maintaining data-centric applications.
• Strong grounding in applied mathematics and/or statistics.
• Autonomous personality who thrives in unstructured conditions.
• Knowledge of actuarial sciences highly regarded.
• Knowledge of blockchain or DeFi technologies highly regarded.

Technical Requirements

• Python data & ML frameworks and tools (e.g. pandas, scikit-learn).
• SQL.
• Bash.
• Git.
• Docker or cloud computing experience desired, but not essential.