Senior SRE & ML Ops Engineer - Real-Time Reliability

Vibe.co; Paris; Hybride; EUR 90 000 - 140 000; Plein temps

Avantages offerts par ce poste

Health insurance

Meal vouchers

Annual offsite

Hybrid flexibility

Tech Syncs

Résumé du poste

Vibe.co in Paris is seeking a performance-focused engineer to own reliability across the production stack – from prediction serving to the bidding engine. You’ll define SLOs, build observability, and lead on-call rigor.

As part of a small team, you’ll reduce p99 latency, optimize the serving path, and partner with data scientists and cross-functional groups to ship resilient infrastructure in a fast-growing ad-tech platform.

Qualifications

• You’ve owned latency-sensitive services in production, on-call included.
• Solid Kubernetes and cloud fundamentals. Debugging p99 latency is your jam.
• Observability experience: metrics, tracing, logs, and alerting decisions.
• Infrastructure as code, CI/CD. You ship fixes, not just find them.
• Comfortable owning systems you didn’t design; you’ll contribute to this stack.

Responsabilités

• Own reliability across the production stack: prediction serving, the bidding engine, pacing, delivery.
• Bring p99 down on the serving path and reduce replicas without sacrificing latency.
• Work on the data layer under real-time serving; Redis comes first.
• Build a way to stress-test the platform end to end in staging.
• Handle capacity planning and infrastructure costs as advertiser volume grows.
• Collaborate with data scientists shipping models into this stack and with Benoît Delsart.
• Run incident response and ensure postmortems translate into changes.
• Collaborate with other engineering teams, notably DSP.

Connaissances

Latency-sensitive systems

Kubernetes

Cloud fundamentals

Observability

Infrastructure as code

CI/CD

On-call readiness

Go/Python/Rust

Outils

Redis

Kafka

Description du poste

Vibe.co in Paris is seeking a performance-focused engineer to own reliability across the production stack – from prediction serving to the bidding engine. You’ll define SLOs, build observability, and lead on-call rigor.

As part of a small team, you’ll reduce p99 latency, optimize the serving path, and partner with data scientists and cross-functional groups to ship resilient infrastructure in a fast-growing ad-tech platform.