Senior Applied ML Engineer: Real-Time LLM Router (Remote)

Creandum; France; A distancia; EUR 107.000 - 160.000; Jornada completa

Ventajas ofrecidas por este puesto de trabajo

Equity options

Remote-first

Learning budget

Annual hackathon

Equipment budget

Extra days off

Descripción de la vacante

Cast AI is seeking an applied-ML platform engineer to own the routing model end to end, including features, objective, training, calibration, and release cadence. You will build production-parity evaluations and compare router-vs-router performance across tasks, using fleet data to derive training signals with clear failure categorization.

Work in a remote-first global environment with Python, PyTorch, SQL, and OpenAI/Anthropic-compatible APIs. Equity options and rapid project cycles await.

Formación

• 5+ years in applied ML or ML research with real-time decision models (ranking, recommender, pricing, or LLM routing).
• Strong Python and SQL at scale; can interrogate millions of records efficiently.
• Experience profiling and shipping models with measurable impact.
• Shaped benchmarks and evaluations for production readiness, including error bars and statistically meaningful results.
• Familiar with serving concerns: TTFT, decode speed, batching, concurrency.

Responsabilidades

• Own the routing model end to end: features, objective, training, calibration, and release cadence.
• Build evaluation systems that gate changes: production-parity benchmarks, router-vs-router comparisons, holdouts by task family.
• Turn fleet data into training signals with clear failure categorization to protect labels.
• Model the objective as user experience: task success × cost × speed under real concurrency.
• Run the online loop: shadow, A/B, full rollout, drift monitoring, retrain if needed.
• Push calibrated decisions and speed-aware routing; balance exploration and exploitation.
• Collaborate with platform engineers on instrumentation and data path requirements.

Conocimientos

Applied ML experience

Python

SQL at scale

Model routing knowledge

Experimentation before shipping

Herramientas

Python

PyTorch

SQL (ClickHouse)

LLM APIs (OpenAI/Anthropic)

RouterBench

GitLab CI

Descripción del empleo

Cast AI is seeking an applied-ML platform engineer to own the routing model end to end, including features, objective, training, calibration, and release cadence. You will build production-parity evaluations and compare router-vs-router performance across tasks, using fleet data to derive training signals with clear failure categorization.

Work in a remote-first global environment with Python, PyTorch, SQL, and OpenAI/Anthropic-compatible APIs. Equity options and rapid project cycles await.