• Ship and debug code on a live, real-time voice pipeline where latency and correctness are user-facing • Design control systems around LLMs: guardrails, budgets, watchdogs, safe fallbacks • Build and operate LLM evaluation and batch-analysis pipelines • Own traditional ML workflows from data to scheduled production inference • Trace production issues from a metric anomaly to root cause, including building the evidence when the cause is a vendor

• Ship and debug code on a live, real-time voice pipeline • Design control systems around LLMs: guardrails, budgets, watchdogs • Build and operate LLM evaluation and batch-analysis pipelines • Own traditional ML workflows from data to scheduled production inference • Trace production issues from a metric anomaly to root cause

• Ship and debug code on a live, real-time voice pipeline • Design control systems around LLMs • Build and operate LLM evaluation and batch-analysis pipelines • Own traditional ML workflows from data to scheduled production inference • Trace production issues from a metric anomaly to root cause

• Ship and debug code on a live, real-time voice pipeline where latency and correctness are user-facing • Design control systems around LLMs: guardrails, budgets, watchdogs, safe fallbacks • Build and operate LLM evaluation and batch-analysis pipelines • Own traditional ML workflows from data to scheduled production inference • Trace production issues from a metric anomaly to root cause, including building the evidence when the cause is a vendor