Senior Neurosymbolic Security Scientist

Socket.dev; Seattle (WA); On-site; USD 167,000 - 226,000; Full time

Job summary

Amazon Leo is seeking an Applied Scientist to join the Engineering and R&D team within Leo Infrastructure and IP Security, with a focus on neurosymbolic reasoning and threat-actor behavior detection. You will drive research into scalable security models and contribute to production deployments that protect the constellation.

The role combines deep scientific exploration with production impact, requiring collaboration with security engineers and software teams to ship robust capabilities at scale.

Qualifications

• 3+ years building ML models for business applications.
• PhD or Master's degree with 6+ years of applied research experience.
• Proficiency in Java, C++, Python or related languages.
• Experience with neural deep learning methods and ML.
• Experience with graphs, knowledge graphs, NLP, embeddings.
• Experience designing evaluation frameworks with human-ground truth and A/B testing.

Responsibilities

• Design and implement scalable neurosymbolic systems that integrate symbolic reasoning over graph-based knowledge representations with LLM agents for security outcomes.
• Design and run reinforcement learning and fine-tuning pipelines (GRPO, PPO, DPO) to optimize language models for security reasoning, triage, and detection-authoring tasks.
• Build behavioral and statistical models to detect threat actor behavior and design evaluation frameworks to measure model performance before production.
• Design and build multi-agent systems that autonomously triage, enrich, and contain security events with safety guardrails and validation mechanisms.

Skills

ML models

Java

C++

Python

Deep learning

Graph algorithms

Knowledge graphs

Unsupervised learning

NLP

Embeddings

Evaluation frameworks

Remediation/mitigation

Stream processing

LLM optimization

Publications

Education

PhD or Master's degree in a relevant field

Tools

R

scikit-learn

Spark MLLib

MxNet

TensorFlow

NumPy

SciPy

Job description

Amazon Leo is seeking an Applied Scientist to join the Engineering and R&D team within Leo Infrastructure and IP Security, with a focus on neurosymbolic reasoning and threat-actor behavior detection. You will drive research into scalable security models and contribute to production deployments that protect the constellation.

The role combines deep scientific exploration with production impact, requiring collaboration with security engineers and software teams to ship robust capabilities at scale.