Ryle Goehausen
Engineer working in Rust, Scala, Python and Spark: data systems, performance engineering, machine learning and distributed systems.
Director of Engineering at Constellation Network, where I lead our open-source project and applied-AI work: DoD / U.S. Air Force supply-chain delivery, LLM security and LLM inference optimization. Before that, a senior engineer at Bloomberg working on Parquet-based portfolio data lakes.
Publications & writing
- Gate AI: LLM Security Benchmark Evaluation Methodology and ResultsRyle Goehausen, Marcus Sousa · arXiv:2606.02959 · 2026
Evaluation harness for prompt-injection and jailbreak detectors: 16 public benchmarks, leakage-controlled cross-validation and one global operating point at ≤1% false-positive rate.
- Frontier models fall to attacks you can scriptGate AI blog · Aug 13, 2026
Fixed, replayable injection payloads compromise leading models.
- Your system prompt is not a security controlGate AI blog · Aug 6, 2026
A defended email agent, one forged message: instruction-based defenses fail where architectural controls hold.
Recent writing
- The importance of remote build servers for agents
- The main job of a software factory is fixing the software factory
- You should be spending as much on CI as you do on AI
- Injecting prompts, memories and reviews at an LLM gateway without breaking the prompt cache
- What I learned running a fleet of AI coding agents
- Single-user speed vs total throughput: reading inference-chip claims