Senior AI Engineer (US)

Assail develops Ares, an autonomous offensive security platform for APIs, web applications, and mobile applications. The Senior AI Engineer will build and improve named-agent architectures, train and evaluate models, extend self-improvement systems, and enhance production reliability and customer-facing accuracy.

Responsibilities:

• Design, implement, and continuously improve the behavior and prompting of Ares' named agents, including orchestration patterns, hand-offs, planning loops, tool use, and shared memory
• Contribute to the model powering Ares across data curation, SFT, preference optimization (DPO/GRPO-style), and evaluation. Own pieces of the training pipeline from dataset construction through eval
• Extend the co-evolutionary self-training system that lets Ares learn from its own engagements and improve over time
• Build false-positive detection, tiered skill learning (suppression rules, agent directives, code-patch proposals), and the infrastructure that routes proposed changes through human approval and back into the platform
• Design rigorous, security-specific evaluations covering OWASP Top 10 coverage, exploit chaining, finding accuracy, and agent reliability. Track performance over every model and agent change
• Contribute to vision capabilities, mobile (iOS/Android) coverage, and BYOK support shipping in Sidewinder and beyond
• Own latency, cost, observability, and failure-mode analysis for agents running in customer engagements. Partner with the platform team on Kubernetes-based deployment
• Contribute to the live accuracy gauge and other surfaces where model and agent quality is exposed to customers