Senior Data Scientist - Graphs & Entity Resolution

TWG Global AI; Santa Monica (CA); On-site; USD 190,000 - 290,000; Full time

Job summary

TWG Global AI is seeking an experienced Graph ML and entity-resolution expert for an onsite Santa Monica/NYC role. You will own the entity graph, develop stable clustering, and detect coordinated behavior across accounts, wallets, and on-chain data.

Production ML and fraud/AML domain experience are highly valued as you collaborate with engineering to scale data sources and markets. The role focuses on building robust graph pipelines, applying embeddings, and delivering real-time, data-driven

Qualifications

• Experience with graph ML, embeddings, or GNNs on large-scale graphs.
• Entity resolution/record linkage at scale.
• Community and cluster detection, embedding-based or classical approaches.
• Track record detecting coordinated or collusive behavior—fraud, AML, or coordinated campaigns.
• Production ML experience: building graph pipelines that run in production.
• Financial-crime, market-surveillance, or trading-domain exposure is a plus.
• DeFi on-chain wallet clustering experience is strongly preferred.

Responsibilities

• Build and maintain the entity graph linking accounts, counterparties, wallets, and behavior into a single picture of who is really acting.
• Develop entity-resolution and clustering methods that stay stable over time, so the same actor is recognized as they resurface.
• Detect coordinated behavior and collusion rings, including cases with no explicit shared identity; DeFi wallet-farming and sybil detection via entity resolution.
• Co-own the Attribution Substrate: fusing vendor attribution clusters with on-chain behavioral clustering into a confidence-scored layer.
• Build graph-based features and representations (embeddings, network features) for the broader detection system.
• Partner with engineering as the graph extends to new data sources and market types.

Skills

Graph ML

Entity resolution

GNNs

Fraud detection

Production ML

Financial-crime AML

Job description

The Organization

At TWG AI, we drive innovation and business transformation across a range of industries—including financial services, insurance, technology, media, and sports—by leveraging data and AI as core assets. Our AI-first, cloud-native approach delivers real-time intelligence and interactive business applications, empowering informed decision-making for both customers and employees.

We prioritize responsible data and AI practices, ensuring ethical standards and regulatory compliance. Our decentralized structure enables each business unit to operate autonomously, supported by a central AI Solutions Group, while strategic partnerships with leading data and AI vendors fuel game-changing efforts in marketing, operations, and product development.

You will collaborate with management to advance our data and analytics transformation, enhance productivity, and enable agile, data-driven decisions. By leveraging relationships with top tech startups and universities, you will help create competitive advantages and drive enterprise innovation.

At TWG, your contributions will support our goal of sustained growth and superior returns, as we deliver rare value and impact across our businesses.

The Role

Manipulation and fraud rarely happen through a single account. The hard problem in surveillance is connecting activity that's deliberately spread across many accounts, wallets, or identities that share no obvious link. You'll own the graph and entity-resolution side of the system: turning trading, account, and on-chain data into networks, resolving many identities to a single actor, and detecting the coordinated rings and collusive clusters that individual-account models miss. The second seat carries this to the DeFi venue, where entity resolution is not one capability among many but the identity substrate itself: the fusion of commercial blockchain attribution with on-chain behavioral clustering that replaces KYC on a pseudonymous exchange.

Key Responsibilities

• Build and maintain the entity graph that links accounts, counterparties, wallets, and behavior into a single picture of who is really acting
• Develop entity-resolution and clustering methods that stay stable over time, so the same actor is recognized as they resurface
• Detect coordinated behavior and collusion rings — including cases with no explicit shared identity; on the DeFi side, wallet-farming and sybil detection as direct outputs of entity resolution
• (DeFi seat) Co-own the Attribution Substrate: fusing vendor attribution clusters (e.g., Chainalysis) with on-chain behavioral clustering into a confidence-scored entity-resolution layer
• Build graph-based features and representations (embeddings, network features) that feed the wider detection system
• Partner with engineering as the graph extends to new data sources and market types

Qualifications

• Strong applied graph ML experience: graph representation learning, embeddings, and/or GNNs on large-scale graphs
• Entity resolution / record linkage at scale, ideally with an eye to cluster stability over time
• Community and cluster detection, both embedding-based and classical approaches
• A track record detecting coordinated or collusive behavior — fraud, integrity, AML, or coordinated-campaign work all translate well
• Production ML experience: you've built graph pipelines that run, not just research notebooks
• Financial-crime, market-surveillance, or trading-domain exposure a plus
• FIX / market-microstructure fluency a plus; for the second seat, on-chain / EVM primitives and wallet-clustering experience strongly preferred

Position Location

This is an onsite position based out of our Santa Monica, CA or New York, NY offices.

Compensation

The base pay for this position is $190,000-290,000. A bonus will be provided as part of the compensation package, in addition to a full range of medical, financial, and/or other benefits.

TWG is an equal opportunity employer, and all qualified applicants will receive consideration for employment without regard to race, color, religion, gender, sexual orientation, gender identity, national origin, disability, or status as a protected veteran.