AI/ML Engineer - Risk & Fraud

Position : AI / ML Engineer (Risk & Fraud)

Overall/Total Experience : 2 - 5 years only

Location : North Delhi

Working Days : 6 Days from Office

Notice Period Requirement : 30 Days (Maximum)

Client's Company Size : Mid-Sized

Roles & Responsibilities :

- Clean, label and analyse SDK identity, device and behaviour data; build reproducible feature and training pipelines with time-based splits that prevent data leakage.

- Check label quality, missing signals and consistency between training features and live inference inputs.

- Develop and compare baseline models for account takeover, bots and scam indicators; combine model outputs and partner-engine signals into useful trust scores.

- Evaluate precision, recall, false positives and performance across customer segments; document failure cases and develop clear reason codes for scores and decisions.

- Use confirmed fraud and false-positive feedback to improve datasets, monitor drift and retrain models; track experiments and validate changes in shadow deployments.

- Collaborate with backend and SDK engineers on reliable, low-latency inference and partner-model integration; support liveness or deepfake evaluation where relevant as the roadmap develops.

Candidate Requirements :

- Strong AI/ML Engineer Profile with hands-on model building, evaluation and reproducible pipelines.

- Must have 2+ years hands-on ML experience with Python, NumPy, pandas and PyTorch or TensorFlow.

- Must have sound foundations in classical ML, neural networks and sequence modelling, with practical experience evaluating imbalanced datasets.

- Must have working knowledge of SQL, exploratory analysis, reproducible pipelines and version-controlled experiments.

- Must be able to clean, label and analyse data and build reproducible feature/training pipelines with time-based splits that prevent data leakage.

- Must be able to develop and compare baseline models, evaluate precision/recall/false positives across segments, and document failure cases with clear reason codes.

- Must be able to explain model trade-offs, investigate errors, and work with engineers to ship and monitor models (drift monitoring, retraining, shadow deployments).

- Must be proficient with agentic AI coding tools, able to review, test and take ownership of generated code.

- Must be from a product company, ideally in fintech is a plus.