- Company Name
- Hyre AI
- Job Title
- AI Engineer
- Job Description
-
**Job Title**
AI Engineer (Data Scientist / AI Engineer)
**Role Summary**
Design, develop, deploy, and maintain real‑time scam‑risk models for a fintech payment intelligence platform. Own the full data‑to‑model‑to‑deployment lifecycle, ensuring that risk decisions are reliable, explainable, and compliant with banking standards.
**Expectations**
- Deliver production‑grade ML solutions with minimal oversight.
- Own all stages: data ingestion, feature engineering, model training, evaluation, deployment, monitoring, and iteration.
- Communicate clearly with cross‑functional teams in a fast‑moving environment.
**Key Responsibilities**
- Build and ship scam‑risk models (typology classification, risk scoring, decision logic).
- Engineer features from heterogeneous signals: transaction context, behavioural sequences, counterparty data, graph/network patterns, and unstructured evidence.
- Design calibrated, explainable outputs (scores + reason codes) aligned with banking workflow requirements.
- Conduct end‑to‑end evaluation: prevent leakage, apply cost‑sensitive metrics, set thresholds, plan phased rollouts, and perform post‑incident analysis.
- Productionise models: package, deploy, monitor, detect drift, and schedule retraining.
- Integrate intelligence into real‑time payment pipelines in collaboration with backend/product teams.
- Optionally support agent/LLM workflows for evidence gathering while maintaining auditability of the core decision process.
**Required Skills**
- Proven experience shipping applied ML to production (not limited to experimentation).
- Advanced Python programming; write maintainable, tested code.
- Strong SQL skills; manipulate large, messy datasets.
- Modeling expertise: calibration, leakage avoidance, bias assessment, threshold tuning, cost‑trade‑off analysis, monitoring, and drift detection.
- Track record in environments demanding reliability, low latency, and explainability.
- Self‑motivated, autonomous work style with clear status communication.
**Nice‑to‑Haves**
- Fraud/scams, payments, risk, trust & safety, AML domain knowledge.
- Experience with graph/network features, entity resolution.
- MLOps tooling: model registry/MLflow, feature stores, orchestration platforms.
- Cloud‑native/event‑driven system familiarity; collaboration with platform/backend engineers.
- Exposure to integrating unstructured signals (text, embeddings, RAG pipelines) into decision systems.
**Required Education & Certifications**
- Bachelor’s or Master’s degree in Computer Science, Data Science, Applied Mathematics, or a related field.
- Relevant certifications (e.g., TensorFlow Developer, AWS Certified Machine Learning, etc.) are advantageous but not mandatory.