Senior Applied ML Engineer | Kimchi (Model Router)
Core
Build and iterate an applied ML model that routes LLM requests to optimize for task success, cost, and latency in a production fleet.
Role type
Senior Applied ML Engineer (Model Router)
Builds
An intelligent model router for LLMs that balances quality, cost, and speed across multiple models.
Domain
Generative AI / LLM Infrastructure / Model Routing
Deliverable
production ML models
Required skills
Applied ML, Python, SQL at scale, LLM evaluation, online A/B testing, drift monitoring, cost/latency modeling
Preferred skills
LLM routing (RouterBench), calibration, conformal methods, online A/B loops with drift monitoring
Technologies
Python, PyTorch, ClickHouse, GitLab CI, OpenAI/Anthropic APIs
Responsibilities
Own the routing model end-to-end (features, objective, training, calibration, release), build production-parity evaluation benchmarks, turn fleet data into training signal, model the objective (success × cost × speed), run the online loop (shadow, A/B, rollout, drift), push frontier techniques (calibration, abstention), partner on instrumentation.
Seniority
Senior, hands-on IC
