Senior Applied ML Engineer — Real-Time Model Router

Cast AI; Italy; Remote; EUR 116,000 - 161,000; Full time

Benefits offered by this job

Remote-first

Equity options

Learning budget

Hackathon

Team events

Equipment budget

Extra days off

Job summary

Cast AI is hiring an applied-ML Platform Engineer to own the routing model end-to-end. You will design features, define objectives, train and calibrate models, and release a faster, more accurate router for every request.

Join a remote-first, globally distributed team that builds a scalable AI routing stack with strong emphasis on benchmarks, latency, and cost efficiency. Equity options and a rapid iteration culture await.

Qualifications

• 5+ years in applied ML or ML research with real-time decision models.
• Strong Python and SQL at scale to interrogate large request-level data.
• You can articulate benchmarks and model performance with receipts.
• You understand serving realities (TTFT, decode speed, batching, concurrency).

Responsibilities

• Own the routing model end-to-end: features, objective, training, calibration, release cadence.
• Build evaluation pipelines: production-parity benchmarks and cross-router comparisons.
• Turn fleet data into training signals while categorizing errors (infra vs task).
• Frame the user experience in terms of task success, cost, and latency under concurrency.
• Lead online experiments: shadow, A/B, and full rollout with drift monitoring.

Skills

Applied ML

Python

SQL at scale

Model routing

Tools

PyTorch

ClickHouse

OpenAI APIs

GitLab CI

Job description

Cast AI is hiring an applied-ML Platform Engineer to own the routing model end-to-end. You will design features, define objectives, train and calibrate models, and release a faster, more accurate router for every request.

Join a remote-first, globally distributed team that builds a scalable AI routing stack with strong emphasis on benchmarks, latency, and cost efficiency. Equity options and a rapid iteration culture await.