Senior Simulation Data Scientist
New York City / San Francisco / Remote /
Gauntlet’s mission is to drive adoption and understanding of the financial systems of the future. Gauntlet is the platform for off-chain intelligence that drives on-chain efficiency in Decentralized Finance (DeFi). We work with protocols to manage risk, improve capital efficiency, and manage incentive spend. We also publish cutting-edge research and aim to take a leading role in defining market risk standards across the industry.
Gauntlet is building infrastructure that allows us to simulate and stress-test blockchain protocols, contracts, and network interactions at scale over a wide range of market conditions. Our models ingest a wide range of on-chain and off-chain data, and are continuously calibrated to the current crypto market structure so that our recommendations are always up-to-date. These models and infrastructure power our platform that currently manages risk and optimizes incentives for over $40B in assets.
You will be working as part of an experienced team that has developed simulation software for many other industries, including high-frequency trading, autonomous vehicles and ride-sharing, and the natural sciences.
- Architecting, implementing, and stewarding end-to-end data infrastructure
- Building agent-based simulations of smart contracts and blockchain networks using our Python SDK
- Designing and optimizing incentive models for blockchain protocols and help discover potential attack vectors
- Build data models and visualizations of public blockchain data and simulation results that provide intuitive analytics to customers
- Understand product, risk, and business requirements and how to apply ML to solve our most challenging problems in impactful ways
- Automating and scaling simulation model deployment on cloud infrastructure
- Make business recommendations to the executive and cross-functional teams (e.g. cost-benefit, forecasting, experiment analysis) effectively through findings from quantitative information
- Driving best practices around security in data engineering
- Driving data literacy and data-driven decision making across functions
- 8-10 years of relevant experience
- Experience developing production quality software in Python, Go, or other high-performance languages
- Experience with scientific computing packages such as Numpy/Scipy, Pandas, etc..
- Track record of designing, building, scaling and maintaining production services, and composing service-oriented architecture
- Experience with distributed computation frameworks such as Spark, Flink, TensorFlow
- M.S. or Ph.D. in STEM field, with experience building production Blockchain pipelines (development, deployment, inference and monitoring) at scale
- Smart contract development experience (e.g. Solidity)
- Experience with building Machine Learning infrastructure at scale