Associate Director, Software Engineering (Guardrail Platform AI Safety Track)

Job description

• Design and build the Guardrail Control Plane to manage AI safety policies, detector configurations, evaluation workflows, and enforcement strategies across enterprise AI applications.
• Develop scalable and extensible guardrail platform capabilities including policy lifecycle management, detector registry, configuration management, versioning, rollout/rollback, and governance workflow, and runtime decision management.
• Design and impllement system architecture and APIs to enable seamless integration between Guardrail Control Plane, Runtime Engine, AI Gateway, RAG, Agent, and other AI platform components.
• Build AI platform observability capabilities providing end-to-end visibility across AI workloads, including request lifecycle tracking, safety decisions, model interactions, performances metrics, cost insight and operational analytics.
• Design and implement LLM tracing solutions using OpenTelemerty / OpenInference to capture AI execution flows including prompts, models calls, retrieval, embedding, tool calls, guardrail checks, and final responses.
• Develop AI safety evaluation and improvement frameworks including datasets management, regression testing pipeline, LLM- as-a-jedge evaluation, human feedback workflows, and production quality monitoring.
• Own hands-on engineering delivery including system design, coding, testing, trobleshooting, performance optimization, and production operation of scalable Guardrail Service.
• Bachelor's degree or above in Computer Science or related discipline, with 8+ years of professional software engineering experience with strong hands-on experience building production-grade backend platforms and distributed systems.
• Proven experience designing and implementing platform systems such as API platforms, workflow platforms, governance platforms, or internal developer platforms.
• Strong system design skills with experience in service architecture, domain modeling, API design, configuration-driven systems, version management, and extensibility patterns.
• Strong hands-on programming experience with Python (FastAPI) and/or Go, with ability to independently design, implement, and operate backend services.
• Experience building configuration management systems, policy engines, workflow systems, rule engines, or platform control planes.
• Experience designing observability platforms including distributed tracting, telemetry pipelines, metrics, dashboards, alerting systems and operational analytics.
• Hands-on experience with LLM observability concepts including prompt tracing, model tracing, retrieval tracing, tool-call tracing, agent workflow tracing, and AI quality monitoring.
• Experience with OpenTelemetry, OpenInference, or similar tracing frameworks.
• Experience integrating AI observability platforms such as Arize Phoenix, Langfuse, LangSmith, MLflow, or similar tools.
• Experience with Kubernetes/Docker and at least one public cloud platform (AWS/GCP/Azure). Tech Stack Python / Go, FastAPI Kubernetes / Docker Redis / PostgreSQL Kafka / PubSub WebSocket / SSE / gRPC OpenTelemetry GCP / AWS / Azure