Senior SRE & ML Ops Engineer — Real-Time Infra Lead

Vibe; Paris; Hybrid; EUR 90,000 - 130,000; Full time

Benefits offered by this job

Variable pay

Hybrid flexibility

Health insurance

Meal vouchers

Annual offsite

Tech Syncs

Job summary

Vibe is seeking a Performance Engineer to own the reliability of the production stack, including prediction serving and the bidding engine, with a focus on latency and cost efficiency. You’ll work closely with data scientists and other engineering teams in Paris, contributing to scalable, observable systems and on-call reliability.

The role emphasizes Kubernetes, cloud fundamentals, and experience with Redis/Kafka, along with IaC and CI/CD practices. Hybrid work setup in Paris offered.

Qualifications

• Latency-sensitive production systems experience, including on-call handling.
• Solid Kubernetes and cloud fundamentals; able to debug p99 latency issues.
• Observability: metrics, tracing, logs; strong alerting judgment.
• Infrastructure as code and CI/CD; able to ship fixes, not just identify problems.
• Comfortable owning systems beyond initial design; accountability for stack performance.

Responsibilities

• Own reliability across the production stack: prediction serving, bidding engine, pacing, delivery; define SLOs and observability.
• Reduce p99 latency; run bidding with fewer replicas without latency loss.
• Work on real-time data layer; optimize Redis access patterns and caching.
• Build end-to-end staging stress tests to find ceilings before production.
• Handle capacity planning and infra costs as ad demand grows.
• Collaborate with data scientists and platform teams to deploy models.

Skills

Kubernetes

Cloud fundamentals

Observability

On-call

Latency tuning

Go

Python

Rust

Tools

Redis

Kafka

Job description

Vibe is seeking a Performance Engineer to own the reliability of the production stack, including prediction serving and the bidding engine, with a focus on latency and cost efficiency. You’ll work closely with data scientists and other engineering teams in Paris, contributing to scalable, observable systems and on-call reliability.

The role emphasizes Kubernetes, cloud fundamentals, and experience with Redis/Kafka, along with IaC and CI/CD practices. Hybrid work setup in Paris offered.