Senior Applied ML Engineer — LLM Router Optimization (Remote)

Cast AI; Netherlands; Remoto; EUR 120.000 - 180.000; Tempo pieno

Vantaggi offerti da questo lavoro

Remote-first global environment

Equity options

Learning budget

Annual hackathon

Equipment budget

Extra days off

Descrizione del lavoro

Cast AI, a remote-first company, seeks an applied ML Platform Engineer to own the routing model end to end, from features to release cadence. You will build production-parity evaluations and convert fleet data into training signals, ensuring calibrated decisions and speed-aware routing.

Expect online experiments, drift monitoring, and close collaboration with the platform team. You will work in a remote-first environment with global impact, equity options, and a strong emphasis on learning and

Competenze

• 5+ years in applied ML or ML research with real-time decision experience.
• Strong Python and SQL at scale for large datasets.
• Able to show publishable or demonstrable results with receipts.
• Know how LLM benchmarks measure performance and cost.
• Understand serving realities like decode speed and batching.
• Instrument before you optimize; include error bars.

Mansioni

• Own the routing model end to end: features, objective, training, calibration, release cadence.
• Build the evaluation that gates changes: production-parity benchmarks and comparisons.
• Turn fleet data into training signals with clear failure categorization.
• Model user-facing objectives: task success × token cost × wall-clock speed.
• Run online loops: shadow, A/B, full rollout, drift monitoring, retrain.
• Push calibrated decisions and abstention under uncertainty for better ROI.
• Collaborate with platform engineers on instrumentation and data pipelines.

Conoscenze

Applied ML

Python

SQL at scale

Model evaluation

A/B testing

Cost-aware routing

Strumenti

Python

PyTorch

SQL (ClickHouse)

LLM APIs

RouterBench

GitLab CI

Descrizione del lavoro

Cast AI, a remote-first company, seeks an applied ML Platform Engineer to own the routing model end to end, from features to release cadence. You will build production-parity evaluations and convert fleet data into training signals, ensuring calibrated decisions and speed-aware routing.

Expect online experiments, drift monitoring, and close collaboration with the platform team. You will work in a remote-first environment with global impact, equity options, and a strong emphasis on learning and