AI Engineer – Trust & Explainability (AI Platform)
Core
Build shared platform capabilities for tracing multi-agent workflows, evaluating non-deterministic outputs, and surfacing meaningful explanations to ensure AI systems are observable, testable, and trustworthy.
Role type
Senior IC AI Engineer (Trust & Explainability)
Builds
End-to-end tracing, correlation capabilities, developer-facing debugging experiences, explanation records, confidence/provenance metadata, and automated quality checks for LLM applications.
Domain
Generative AI / Multi-agent systems / Observability / Application Security
Deliverable
production ML models
Required skills
Python, TypeScript, LLM integration, distributed tracing, automated testing, cloud infrastructure (AWS/Azure), adversarial testing, multi-tenant security
Preferred skills
OpenTelemetry, GenAI semantic conventions, Langfuse/Arize Phoenix/LangSmith, open-source contributions, financial services domain experience
Technologies
Python, TypeScript, AWS, Azure, Docker, Git, OpenTelemetry, Langfuse, Arize Phoenix, LangSmith, promptfoo, DeepEval
Responsibilities
Build end-to-end tracing across AI platform components including gateways, orchestration, and model calls; Develop explanation capabilities transforming raw traces into human-readable accounts; Create platform primitives for customer-facing trust including confidence and provenance metadata; Develop automated quality checks for model, prompt, and tool changes; Build adversarial and red-team testing for prompt injection and data-exfiltration risks; Partner with product engineering to integrate trust capabilities into production applications.
Seniority
Senior, hands-on IC