Careers: Build the Fastest Path to Real-Time AI

Qorinix hires high-ownership builders who want to ship measurable performance outcomes in AI infrastructure. We emphasize execution depth, technical judgment, and production accountability.

Engineering team collaboration in high-technology workplace
Execution rhythmBi-weekly release loops
Ownership modelSmall teams, high autonomy
Technical scopeRuntime + API + platform controls
Hiring intentSenior individual contributors

Role Families

Inference Engineering

Runtime orchestration, queue policy, and low-latency execution controls.

Model Optimization

Model serving efficiency, quantization workflows, and response-quality tuning.

Reliability & Platform

SLO design, incident systems, observability depth, and operational safety.

Open Roles

Inference Runtime Engineer

Engineering Full-time London / Remote (EU)

Own request flow from API ingress to runtime scheduling and latency stabilization.

Responsibilities

  • Design low-latency routing and queue arbitration for mixed workloads.
  • Improve p95/p99 performance under burst scenarios.
  • Ship instrumentation and rollback-safe runtime changes.

Requirements

  • Strong distributed systems and backend runtime experience.
  • Hands-on delivery of measurable latency improvements in production.
  • Clear incident and debugging communication standards.

Impact

Direct ownership of speed and throughput quality across customer-critical inference paths.

Model Optimization Engineer

Applied AI Full-time London / Remote (EU)

Improve model-serving performance and response economics across production model lanes.

Responsibilities

  • Optimize serving stacks through quantization and batching strategies.
  • Translate benchmark evidence into shippable runtime improvements.
  • Tune domain-specific model variants for response speed and stability.

Requirements

  • Experience with transformer inference and model-serving pipelines.
  • Strong experiment rigor and reproducibility discipline.
  • Cross-functional collaboration with runtime and platform teams.

Impact

Own the bridge between model behavior and infrastructure-level performance outcomes.

Platform Reliability Engineer

Platform Full-time London / Remote (EU)

Lead reliability design across API runtime, billing consistency, and incident readiness.

Responsibilities

  • Define SLOs and reliability controls across core product surfaces.
  • Build incident runbooks and operational resilience workflows.
  • Improve observability for latency, quota, and webhook integrity signals.

Requirements

  • Production SRE/Platform operations experience in high-scale services.
  • Security-aware approach to access and release governance.
  • Operational calm under high-pressure production events.

Impact

Protect customer trust by stabilizing runtime quality and escalation effectiveness.

Developer Platform Engineer

Developer Experience Full-time London / Remote (EU)

Own API onboarding quality, documentation reliability, and production integration pathways.

Responsibilities

  • Design API integration flows and implementation templates.
  • Improve onboarding conversion from signup to first successful workload.
  • Maintain docs aligned with real runtime behavior and constraints.

Requirements

  • Strong API/backend engineering with product-facing communication.
  • Track record of improving developer adoption and onboarding speed.
  • Ability to simplify complex infrastructure decisions.

Impact

Accelerate customer activation and reduce friction from pilot to production.

Hiring Process

01

Profile Review

Role-scope alignment and technical depth screening.

02

Technical Interview

System design judgment and production tradeoff quality.

03

Work Simulation

Realistic scenario evaluation tied to job responsibilities.

04

Panel Discussion

Cross-functional collaboration and ownership assessment.

05

Decision

Final calibration and offer discussion.

Candidate Standards

  • Evidence of shipping production-grade systems with measurable performance impact.
  • Strong written communication for specs, incident notes, and decision logs.
  • Comfort with security, governance, and release-quality accountability.
  • Execution-first mindset with high ownership and low-ego collaboration.