Careers
We are hiring senior builders who want to ship real performance gains, not slide-deck architecture. If you care about latency, throughput, reliability, and execution quality, Qorinix is built for your kind of work.
Open Roles
Inference Runtime Engineer
Own request flow from API ingress to model execution, including queue policy, routing policy, and burst handling.
Responsibilities
- Design and optimize low-latency request routing for mixed workload profiles.
- Improve p95/p99 stability during traffic bursts and failure scenarios.
- Build performance instrumentation and release-safe runtime rollouts.
- Partner with model and reliability teams on production tuning loops.
Requirements
- 3+ years in distributed systems, backend infrastructure, or runtime engineering.
- Strong knowledge of concurrency, async processing, and failure recovery.
- Proven experience shipping measurable latency improvements in production.
Model Optimization Engineer
Drive model serving efficiency across quantization, scheduling, token economics, and runtime-kernel interactions.
Responsibilities
- Optimize response latency and throughput for production model-serving paths.
- Run benchmark loops and convert test signals into deployable improvements.
- Tune model variants for domain-specific workloads and predictable cost.
- Work with runtime engineers to close the gap between model and infra performance.
Requirements
- Hands-on experience with transformer inference and serving pipelines.
- Practical optimization skills in quantization, batching, and token efficiency.
- Strong engineering discipline in experiment design and result reproducibility.
Platform Reliability Engineer
Build service reliability across API, billing, webhook, and admin-control pathways with clear incident ownership.
Responsibilities
- Define SLOs and enforce reliability guardrails for production workloads.
- Build incident response workflows and post-incident corrective systems.
- Harden operational safety for release pipelines and privileged actions.
- Improve observability depth across latency, usage, and billing integrity signals.
Requirements
- Strong experience in observability stacks, incident management, and SRE practices.
- Practical security mindset for access control and production change governance.
- Ability to balance speed with reliability under high execution pressure.
Developer Platform Engineer
Own API onboarding quality, developer docs, SDK pathways, and integration reliability for production customers.
Responsibilities
- Build clear API integration pathways and production-ready developer tooling.
- Improve onboarding funnel from account creation to first successful workload.
- Maintain docs and examples tied directly to real platform behavior.
- Collaborate with product and runtime teams on API ergonomics and reliability.
Requirements
- Strong backend/API engineering experience with developer-first thinking.
- Ability to translate complex infrastructure into usable interfaces and docs.
- Track record of improving developer adoption and activation metrics.
Hiring Process
Application Review
Profile and project review with role-fit assessment.
Technical Screen
Practical engineering depth and systems decision quality.
Work Sample
Hands-on scenario aligned to the role’s real production context.
Panel Interview
Cross-functional discussion on ownership, execution, and collaboration.
Final Decision
Reference checks, role alignment, and compensation package.
Benefits & Working Model
Compensation Philosophy
Competitive base salary with performance-aligned upside tied to long-term company value.
Work Design
High-trust hybrid/remote operating mode with strong ownership and clear delivery expectations.
Growth Environment
Direct exposure to architecture, product, and customer outcomes from early-stage execution cycles.
General Requirements
- Strong engineering communication in written specs, incident notes, and architecture reviews.
- Evidence of shipping production systems with measurable performance improvements.
- Comfort working across API platform security, governance controls, and release engineering.
- Execution-first mindset with clear ownership, low-ego collaboration, and operational discipline.
Candidate FAQ
Do you sponsor relocation?
For selected senior roles, yes. It depends on role criticality and hiring timeline.
Do you support remote work?
Yes. We support hybrid and remote hiring depending on timezone overlap and role scope.
How fast is the process?
Typical process is 2-3 weeks from first interview to final decision for active openings.
What matters most in hiring?
Execution quality, ownership, technical judgment, and ability to deliver measurable outcomes.