← Back to All Openings

Staff Platform Engineer – Federated Explainability & Differential Privacy

corpora-jobs-1778796293285-db9d41c6 - Frontier Development
Platform EngineerStaff1 position

Why This Role is Different

Frontier Development Role

Architect and ship a privacy‑first federated learning platform that lets agents collaborate on explanations without leaking sensitive data—essential for regulated, multi‑agent deployments.

The Frontier Element

You will build the first end‑to‑end system that combines federated learning, differential privacy, and explainability in a single pipeline, a combination that has not yet been demonstrated at scale in production.

🔬

Project Context

Research Area

Federated Explainability with Differential Privacy (FED‑EXP)

From: Overfitting of Explainability Models to Benign Data

Why This Role is Critical

FED‑EXP requires a robust, privacy‑preserving federated learning infrastructure that can share explanation gradients while respecting differential privacy budgets. This role will design and implement the end‑to‑end pipeline, ensuring compliance, scalability, and low‑latency inference.

What You Will Build

A federated training framework that injects DP noise into explanation gradients, a secure aggregation protocol, and an explanation‑serving API that delivers SHAP/LIME maps without exposing raw data. The deliverables include a privacy‑budget manager, a monitoring dashboard, and a production‑grade deployment on Kubernetes.

🛠

Key Responsibilities

  • Design the federated learning architecture (FedAvg/FedProx) with DP noise injection on explanation gradients.
  • Implement secure aggregation and client‑side clipping to bound sensitivity.
  • Develop a privacy‑budget manager that tracks ε‑δ across training rounds.
  • Integrate explanation tools (SHAP, LIME) into the aggregated model and expose them via a REST/GRPC API.
  • Deploy the pipeline on Spark/Kubernetes, monitor latency and privacy metrics with Prometheus/Grafana.
🎯

Required Skills & Experience

Technical Must-Haves

Federated learning frameworks (TensorFlow Federated, PySyft)

Expert
Build and tune federated training loops.

Differential privacy algorithms (DP‑SGD, DP‑Noise)

Advanced
Inject noise into gradients and manage budgets.

Secure aggregation protocols (Secure Multi‑Party Computation)

Proficient
Ensure privacy during gradient aggregation.

Explainability libraries (SHAP, LIME, Captum)

Proficient
Generate post‑hoc explanations from federated models.

Distributed systems (Spark, Kubernetes, gRPC)

Expert
Deploy and scale the federated pipeline.

Experience Requirements

  • 5+ years building production‑grade federated or distributed ML systems.
  • Hands‑on experience with DP in real‑world deployments.
  • Track record of delivering low‑latency inference services.

Education

Master’s or PhD in Computer Science, Electrical Engineering, or a related field with a focus on privacy or distributed systems.

Preferred Skills

  • Experience with regulatory compliance for AI (GDPR, EU AI Act).
  • Knowledge of LLM fine‑tuning and prompt engineering.
🤝

You Will Thrive Here If...

  • Self‑directed and results‑oriented, with a bias toward shipping.
  • Comfortable navigating ambiguous privacy requirements and turning them into concrete engineering solutions.
  • Strong communication skills to explain privacy guarantees to non‑technical stakeholders.
📈

Impact & Growth

12-Month Impact

Within 12 months, launch a federated explainability platform that achieves <0.1% privacy leakage, supports 100+ client nodes, and delivers SHAP explanations with <200 ms latency, enabling compliance‑ready deployments in finance or healthcare.

Growth Opportunity

Lead the expansion of the privacy‑first platform to multi‑tenant, cross‑border deployments, and mentor a growing team of platform engineers.

Ready to Push the Boundaries?

If this sounds like the challenge you have been looking for, we want to hear from you. We value what you can build over where you have been.