[Hiring] Staff Engineer @MOXFIVE

Role Description

You'll extend what our agents can do, measure whether their findings hold up, and keep the services around them solid as the platform grows. This is a hands-on role, and most of your time goes to designing and building.

• Agent Capabilities: Adding investigation tools and integrations with security data sources, and improving how agents manage context, recall evidence, and trade off cost against latency.
• Investigation Quality: Building the evaluations that show whether agents reach correct, well-sourced findings, and using them to decide model, prompt, and tool changes.
• Platform Architecture: Evolving service boundaries and failure handling as new capabilities land.
• Engineering Standards: Raising our practices for API governance, testing, and observability.
• Cross-Functional Leadership: Working with product management to turn case needs into technical specifications.

Qualifications

• Track Record: You've designed and shipped distributed systems that are still running in production years later, and you can tell us what you'd change. Typically this comes from time in a Staff, Principal, or Lead role.
• AI/LLM Engineering: You've taken AI agents from prototype to production across multiple model providers, and built tool-calling agent loops, evaluation harnesses that catch regressions before release, and guardrails against hallucination.
• AI-Native Development: You build with coding agents every day and know how to review and verify what they produce.
• Language Expertise: Deep expertise in Go or Python and strong in the other, including the runtime, concurrency models, and memory management of each.
• Data Architecture: You've worked across a relational system of record, columnar analytical stores that query large datasets, and vector search. You know when each fits, and you've run zero-downtime schema migrations.
• API Design: You've designed schema-first, contract-driven APIs with generated clients and built-in validation, including streaming APIs for live updates.
• Durable Systems: You've built long-running workflows on durable execution and event streaming, and you treat idempotency, retries, and recovery from partial failure as design requirements.
• Data Pipelines: Experience building event-driven ingestion pipelines that move large volumes of structured data from object storage into analytical systems.

Nice to Have

• Cloud Architecture: Experience with a major cloud provider, infrastructure as code, and container orchestration, including designs that keep each customer's or case's data isolated.
• Security Domain: Experience building security products, or familiarity with digital forensics, incident response, or security telemetry.