GenAI Evaluation Engineer (Риски) (Python)

Why Socure?

Socure is building the identity trust infrastructure for the digital economy — verifying 100% of good identities in real time and stopping fraud before it starts. The mission is big, the problems are complex, and the impact is felt by businesses, governments, and millions of people every day.

We hire people who want that level of responsibility. People who move fast, think critically, act like owners, and care deeply about solving customer problems with precision. If you want predictability or narrow scope, this won’t be your place. If you want to help build the future of identity with a team that holds a high bar for itself — keep reading.

WHY SOCURE?

Socure is building the identity trust infrastructure for the digital economy — verifying 100% of good identities in real time and stopping fraud before it starts. The mission is big, the problems are complex, and the impact is felt by businesses, governments, and millions of people every day.

We hire people who want that level of responsibility. People who move fast, think critically, act like owners, and care deeply about solving customer problems with precision. If you want predictability or narrow scope, this won't be your place. If you want to help build the future of identity with a team that holds a high bar for itself — keep reading.

ABOUT THE ROLE

We are looking for a Staff Data Scientist to join Socure's Watchlist Data Science team. Watchlist sits at the heart of global AML compliance — our platform screens hundreds of millions of entities in real time across sanctions lists, PEP databases, and adverse media sources for banks, fintechs, and payment companies worldwide.

As a Staff Data Scientist, you will work on the hardest problems in entity matching and classification: scaling our patented real-time matching engine, building advanced Natural Language Processing (NLP) models for Named Entity Recognition (NER) and Information Extraction, and bringing next-generation research to production. This is a senior individual contributor role with broad technical ownership and direct impact on a product that helps the world's financial institutions manage sanctions and AML risk.

WHAT YOU'LL DO

Data Quality & Enrichment

• Improve the quality, coverage, and freshness of Watchlist's underlying data through next-generation ingestion pipelines.

• Design and execute rigorous data quality analysis pipelines to identify anomalies, evaluate dataset health, and ensure high-fidelity inputs for downstream model training.

• Apply NLP and AI to classify and enrich raw source data into normalized schemas — extracting structured entity attributes from unstructured sanctions, PEP, adverse media, and enforcement sources.

• Expand multilingual capabilities to support global screening across Latin and non-Latin scripts.

Entity Resolution

• Build and improve NLP systems that consolidate how watchlist identities are represented. Developing Information Extraction and Named Entity Recognition (NER) pipeline to deduplicate entities across lists and resolve aliases into canonical profiles..

• Develop approaches to handle how entity profiles change over time as names, aliases, and sanctions status evolve.

• Measure and benchmark entity resolution quality, driving continuous improvement in coverage and accuracy.

Match Engine & Risk Scoring

• Design and scale advanced NLP models and algorithms that perform real-time name matching and identity classification across diverse, multilingual unstructured data sources.

• Build multi-signal risk scoring that combines name similarity, entity type, geography, list type, and other attributes into unified, calibrated risk scores.

• Maintain and improve benchmarking frameworks, golden datasets, and regression tests that keep the match engine at the highest levels of recall and precision.

Analytics, Tuning & Evaluation

• Build models and analytics that help customers tune their screening thresholds to the right operating point for their risk appetite and entity mix.

• Develop backtesting and counterfactual analysis capabilities so customers and internal teams can understand how model or threshold changes would affect screening outcomes.

• Design evaluation frameworks for AI-powered autonomous decision systems — defining correct behavior, calibrating confidence thresholds, and monitoring for drift in production.

AML Risk Detection

• As Watchlist expands into payment screening, build the mathematical analysis and feature engineering needed to detect AML risk patterns across transaction data and payment message fields.

• Develop and maintain the AML taxonomy and risk signal library that underlies Watchlist's classification and detection capabilities.

• Apply graph-based methods to surface indirect risk exposure — identifying entities connected to sanctions risk even when they are not directly listed.

Research & Technical Leadership

• Lead technical initiatives across Watchlist Data Science and shape the team's long-term approach to entity matching, enrichment, and AI.

• Collaborate closely with Product and Engineering to translate research into production-grade systems at scale.

• Stay current with advances in NLP, large language models, and entity resolution; prototype and deploy relevant techniques (e.g., advanced NER, LLM-based extraction) to AML use cases.

• Mentor peers and contribute to a culture of technical rigor and continuous improvement.

WHAT YOU BRING

• Master's or PhD in Computer Science, Computational Linguistics, Statistics, Applied Mathematics, or a related field; or equivalent professional experience.

• 7+ years of experience in data science or machine learning, with meaningful work in NLP, entity resolution, or information extraction.

• Experience in AML, sanctions screening, adverse media, or financial crime detection is strongly preferred.

• Hands-on experience building and deploying NLP pipelines for entity extraction, named entity recognition, and record linkage at production scale.

• Familiarity with multilingual NLP and non-Latin script processing is a strong plus.

• Experience with LLMs and agentic AI frameworks (e.g., LangChain/LangGraph) is a plus.

• Strong proficiency in Python and major ML libraries (PyTorch, spaCy, HuggingFace Transformers).

• Strong SQL proficiency and experience with large-scale data pipelines and production ML systems.

• Excellent communication skills — able to translate model performance tradeoffs into compliance and business language for non-technical audiences.

Note: We cannot provide Sponsorship at this time.

You must be located in one of our talent hubs: New York, San Francisco, Seattle, or Miami.

Socure is an equal opportunity employer that values diversity in all its forms within our company. We do not discriminate based on race, religion, color, national origin, gender, sexual orientation, age, marital status, veteran status, or disability status. If you need an accommodation during any stage of the application or hiring process — including interview or onboarding support — please reach out to your Socure recruiting partner directly.

Socure is an equal opportunity employer that values diversity in all its forms within our company. We do not discriminate based on race, religion, color, national origin, gender, sexual orientation, age, marital status, veteran status, or disability status.
If you need an accommodation during any stage of the application or hiring process—including interview or onboarding support—please reach out to your Socure recruiting partner directly.

Follow Us!

YouTube | LinkedIn | X (Twitter) | Facebook

Управление Модельных Рисков - «by-design» уникальное подразделение, которое «видит» все AI/ML модели Банка, понимает процессы/точки принятия решений моделями, кривая обучения у наших сотрудников «круче», чем в подразделениях, разрабатывающих модели.

Наша цель – помочь Банку зарабатывать больше и улучшать клиентский опыт за счет повышения эффективности моделей и их использования в Бизнес процессах.

Мы ищем DS/Quant с экспертизой на стыке финансовой математики, торговых алгоритмов и ML для работы в напралении Модельного Риска Торговой Книги. Вы будете выступать ключевым звеном контроля качества моделей и агентов, используемых в оценке рисков и ценообразовании финансовых инструментов.

Обязанности

• оценка качества моделей ClassicML, работающих на финансовых рынках, в том числе: торговые алгоритмы, оценка эластичности по цене, кластеризация клиентов и т.д.
• проведение независимой оценки качества моделей прайсинга финансовых инструментов, а также риск-моделей (включая VaR, CVA, PFE)
• анализ корректности математических предпосылок, устойчивости моделей и их соответствия бизнес-требованиям и рыночным условиям
• оценка и контроль рисков агентов, работающих в торговых алгоритмах, процессах прайсинга финансовых инструментов и оценки рыночных рисков
• создание инструментов для автоматизации процессов мониторинга моделей и агентов с использованием Python
• подготовка аналитических заключений по результатам валидации, формирование рекомендаций по доработке моделей
• презентация результатов работы, аргументация выводов и защита предложенных решений перед разработчиками моделей, риск-менеджментом и бизнес-заказчиками.

Будет плюсом:

• навыки работы с генеративными AI-моделями; опыт создания AI-агентов и использования их в работе будет преимуществом.

Требования

• знание теории вероятностей, математической статистики и случайных процессов
• опыт работы на стороне разработки или валидации ClassicML моделей
• уверенные навыки программирования на Python, опыт разработки структурированного и поддерживаемого кода
• знание базовых принципов построения моделей прайсинга производных финансовых инструментов
• опыт работы с количественными моделями в финансах или смежных областях будет преимуществом
• участие в летних школах или курсах: Vega, ЦМФ – также является преимуществом.

Условия

• работа в удобном и современном офисе недалеко от станции метро Кутузовская
• ежегодный пересмотр зарплаты, годовая премия
• корпоративный спортзал и зоны отдыха
• более 400 образовательных программ СберУниверситета для профессионального и карьерного развития
• расширенный ДМС, льготное страхование для семьи и корпоративная пенсионная программа
• гибкий дисконт по ипотечному кредиту, равный 1/3 ключевой ставки ЦБ
• подписка Прайм с возможностью совместного использования на трёх близких
• вознаграждение за рекомендацию друзей в команду Сбера.