Quick overview
Job description
role overview
as a fraud analyst at CRED, you’ll work at the intersection of data, technology and fraud prevention to identify and prevent emerging fraud patterns across products.
fraud patterns continue to evolve, making it important to identify and address emerging risks and vulnerabilities. you’ll think like an adversary -analyse data and system behaviour, spot unusual patterns and vulnerabilities, and work closely with data science, product and engineering teams to build practical solutions that prevent fraud.
this is a hands-on problem-solving role. you don’t need to be a fraud expert or a deep ml specialist. what matters is strong analytical and coding fundamentals, curiosity, and the ability to approach problems from first principles.
what will you do?
-
analyse large datasets to identify unusual patterns, behaviours and signals that could indicate emerging fraud.
-
investigate how fraudsters may be exploiting products, processes or system vulnerabilities.
-
develop hypotheses, test them through data and translate findings into practical fraud detection approaches.
-
work with data science and engineering to identify and close gaps in fraud detection and prevention.
-
identify new signals and approaches that can improve our ability to detect evolving fraud patterns.
-
build and iterate on detection logic and solutions as fraud patterns and attack methods change.
-
partner with product and engineering teams across cred to understand new product flows and identify potential fraud risks.
-
work closely with engineering to implement signals, controls and other prevention mechanisms.
-
operate across different products and problem statements as fraud is a horizontal problem across CRED.
-
stay curious about how systems work and how they can be exploited.
-
learn continuously as new fraud patterns, technologies and vulnerabilities emerge.
-
bring an adversarial / "hacker" mindset to problem solving , think beyond the obvious solution and challenge existing assumptions.
fraud detection & analysis:
fraud prevention & problem solving:
cross-functional execution:
continuous learning:
you should apply if you:
-
have 1–2 years of experience in data science, analytics, engineering or a related technical role.
-
have strong sql and analytical skills and are comfortable working with large datasets.
-
have good hands-on python/coding experience.
-
have a basic understanding of data science /ML concepts such as features, models and how models are deployed. you do not need to be an ml specialist or have built fraud models before.
-
are highly curious and willing to learn, especially in ambiguous and unfamiliar problem spaces.
-
have an adversarial / hacker mindset you naturally think about how a system might be broken, exploited or circumvented.
-
are comfortable getting hands-on and working closely with engineering and product to take an idea from analysis to implementation.
-
have strong ownership and grit, and are comfortable operating with urgency when the problem demands it.
