Senior Applied ML Engineer | Kimchi (Model Router)

Requisitos

• 5+ years in applied ML or ML research, having trained, evaluated, and shipped models that make real-time decisions (ranking, recommendati..
• Strong Python and SQL at scale — can pull, clean, and interrogate millions of request-level records independently
• Can tell the difference between a model that got better and an eval that got easier
• Has real opinions about what LLM benchmarks measure, agentic harnesses included
• Knows serving reality: TTFT, decode speed, batching, prefix caching, concurrency

Desejáveis

• Prior work on LLM routing specifically: RouterBench-class evals, cost/quality/latency Pareto fronts
• Calibration, abstention, or conformal methods in production decision systems
• Has run online A/B loops with drift monitoring on a model that touches real money