Data Scientist — Blockchain Intelligence
About Merkle Science:
Merkle Science offers blockchain transaction monitoring and intelligence solutions for various sectors to identify and prevent illicit usage of cryptocurrencies. The company aims to enhance the safety and regulatory compliance of cryptocurrencies by providing robust infrastructure.
Merkle Science has a presence in New York, Singapore, Bangalore, and London, bringing together a team with diverse experience from reputable organizations like Bank of America, PayPal, and Amazon. It has secured significant investments from various entities.
About the Role:
The role involves converting raw blockchain activities into reliable intelligence by attributing addresses to real-world entities and businesses. The focus is on discovering risks for compliance guidelines and investigations. As a data scientist, you will collaborate with attribution and clustering leads on developing models and heuristics across multiple chains such as Bitcoin, Ethereum, Tron, Solana, etc.
Responsibilities:
- Develop, test, and implement clustering and attribution heuristics with a data-driven approach for precise metrics evaluation.
- Take full ownership of the data processes from extraction to modeling to steer clear of external dependencies.
- Establish and maintain production pipelines, including addressing edge cases and translating outcomes into reusable logic.
- Engage with investigations and product teams to define ideal outcomes and measure against actual results.
- Prototype efficiently and refine successful solutions for long-term use.
Requirements:
- Over 4 years of experience building data science or data engineering systems with hands-on implementation.
- Proficiency in Python and SQL for handling large datasets, joins, and processing challenges at scale.
- Strong grasp of clustering, graph analyses, or entity investigations with a focus on result verification.
- Capacity to navigate precision versus coverage trade-offs and defend chosen metrics.
- Self-directed attitude to tackle ambiguous problems, acquire data, and steer projects towards successful outcomes.
Tech Stack:
The daily tools include Databricks for data processing, Kafka for real-time data ingestion, Python for coding, and TigerGraph for graph database operations. Additionally, expertise with SQL, ClickHouse, orchestration tools, Git, GitHub, and GCP for cloud environment will be beneficial.
Working Style:
Operate within a small, collaborative team with high levels of ownership and minimal red tape. A focus on quick prototyping, transparent measurement, and efficient project delivery shapes the work dynamics.
Well-Being, Compensation, and Benefits:
Merkle Science values employee well-being, providing comprehensive health insurance, flexible time off, personal development opportunities, and work/life balance. Regular team-building events and mental health discussions are encouraged. Competitive compensation packages and equity grants are offered to recognize talent and foster career growth within the organization.
Additional Note:
The recruitment process may include AI tools for some aspects; however, final hiring decisions are made by individuals. For more details on data processing procedures, feel free to reach out to us.
