Senior Data Scientist
Chainalysis is a blockchain analysis company that provides data, software, and services to investigate and prevent cryptocurrency-related fraud and money laundering.
Projects
About Chainalysis
Chainalysis is a blockchain analysis company that offers comprehensive data, software, and services to government agencies, financial institutions, exchanges, and cybersecurity firms. Their solutions include Chainalysis Reactor for tracing blockchain transactions and Chainalysis KYT for real-time transaction monitoring. Chainalysis supports compliance with anti-money laundering and counter-terrorism financing regulations, helping clients investigate illicit activities and ensure regulatory adherence.
Skills
About the Role
You'll join the Research and Intelligence organisation in London, sitting within the Account and Smart Contracts research chapter as part of a broader eleven-person team developing behavioural heuristics, graph algorithms, and machine learning techniques that power blockchain analysis. Your work will directly shape the data that fuels products and customers across the globe. You'll tackle deeply technical, ambiguous problems at the intersection of data science, graph computation, and on-chain analysis, taking ownership of projects end-to-end.
Requirements
- A PhD in computer science, machine learning, statistics, physics, mathematics, or a related technical field – or equivalent industry experience working on advanced, data-intensive problems
- Expert-level proficiency in Python and SQL, with a track record of writing clean, testable, production-quality code
- Demonstrated experience applying advanced analytical techniques (e.g. graph algorithms, ML, statistical inference) to large, messy datasets
- Comfort working with EVM-based blockchain data, or strong evidence of the aptitude to ramp up quickly on EVM data structures and protocols
- A demonstrated ability to take ownership of projects: decomposing requirements, driving them to completion, and proactively seeking clarity from stakeholders
- An analytical, open-minded approach to problem solving – comfortable navigating ambiguity and willing to dive into problems outside your day-to-day scope
- Strong written and verbal communication skills, including the ability to explain complex methodology to diverse audiences
- Familiarity with Databricks, DBT, Spark/PySpark, or similar large-scale data platforms (preferred)
- Modified infrastructure-as-code (e.g. Terraform) or contributing to production data pipelines (preferred)
- Mentored junior data scientists or engineers (preferred)
- Knowledge of, or passion for, the cryptocurrency and blockchain space (preferred)
Responsibilities
- Own the execution of one or more production data science projects, translating broad problem statements into well-scoped tasks and credible analytical results
- Design, develop, and validate novel behavioral heuristics and algorithms over EVM (and other) blockchain data to attribute on-chain activity and uncover new insights
- Apply advanced techniques including graph computation, statistical modeling, and machine learning to large-scale on-chain datasets
- Identify and resolve inefficiencies in code, methodology, and workflows; ensure work integrates cleanly into the production data and tooling stack
- Clearly articulate and defend methodology and results to technical and non-technical stakeholders
- Mentor junior team members, contribute to technical hiring, and share knowledge
- Collaborate closely with peers to bring research from prototype to production
