About Runware
Runware is building a high-performance, full-stack AI media-creation platform — empowering developers and companies to generate any type of media instantly. As we scale fast and integrate increasingly complex models, we need stronger visibility, analytics, and monitoring across the whole platform stack.
We’re looking for a Data Expert (Analytics + Monitoring + Observability) to help us better understand, measure, and optimize how the Runware platform performs at scale — internally and for our clients.
🎯 Mission
Your main goal is to give Runware full visibility over:
End-to-end inference performance
Integration usage and model activity
Errors, delays, bottlenecks, regressions
Internal and client-facing analytics dashboards
Health and performance of production pipelines
You will provide the data insights that allow engineering, ML, backend, DevOps, and leadership to make informed decisions — and to continuously improve performance and reliability.
🧩 What You Will Do
Performance Monitoring & Benchmarking
Build and maintain E2E inference time tracking (global and per-model).
Monitor how implementation changes impact total request latency.
Detect regressions introduced by suboptimal code paths.
Provide automated alerts & historical trends.
Usage & Analytics Reporting
Build dashboards for internal use (engineering, product, leadership).
Provide client-facing usage dashboards (requests, errors, success rate, performance).
Support clients who need visibility to debug their integrations.
Track model-level usage, API endpoints usage, adoption metrics, etc.
Platform Observability
Implement metrics, logs, and traces that help the entire platform scale smoothly.
Work closely with DevOps & backend teams to improve system observability.
Provide insights that guide infra decisions (GPU allocation, autoscaling, caching, batching, etc.).
Data Infrastructure Ownership
Select and maintain tooling (e.g., Prometheus/Grafana, Datadog, OpenTelemetry, ELK, BigQuery, etc.).
Ensure data pipelines are reliable, accessible, and always up-to-date.
Build simple, easy-to-read dashboards for both technical and non-technical teams.
Requirements
Must-Have
Strong experience with data analytics, observability, or monitoring
Hands-on with metrics/logging/tracing frameworks (Prometheus, Grafana, Datadog, New Relic, etc.)
Good understanding of backend systems and distributed architectures
Ability to turn raw metrics into actionable insights
Experience building dashboards for internal and external stakeholders
Familiarity with AI model monitoring (latency, throughput, error codes, GPU utilization)
Nice-to-Have
Experience with AI/ML infrastructure, inference pipelines, GPUs
Understanding of Python APIs, FastAPI, or Node environments
Experience working with high-throughput real-time systems
Startup or scale-up experience
What You Bring
A problem-solver mindset
Proactivity — you like digging into the data and flagging problems before anyone else sees them
Ability to work with ML, backend, DevOps, and product teams
Comfort with autonomous ownership
You help Runware go from “it works” to “we know exactly how well it works — and how to make it better.”
Benefits
We’re a remote-first collective, meeting in person twice a year to plan, brainstorm, celebrate wins, and enjoy some face-to-face time. We have core hours for cooperative working and calls, but outside of that your calendar is yours. Work the hours that let you perform at your peak while also building a healthy life.
Our release cycles are fast and intense, but they’re followed by real downtime. After big pushes we expect the team to unplug, recharge, and come back ready & stronger than ever for the next leap.
Generous paid time off – vacation, sick days, public holidays
Meaningful stock options – share in the upside you create
Remote-first setup – work from home anywhere we can employ you
Flexible hours – own your schedule outside core collaboration blocks
Family leave – paid maternity, paternity, and caregiver time
Company retreats – twice-yearly gatherings in inspiring locations
Runware is building an API layer for next-generation AI products that provides teams with fast, reliable access to real-time inference across thousands of models through a single flexible API. The platform enables customers to build and scale media generation products with better performance, lower cost, and reduced operational complexity. Behind this is an infrastructure platform built for speed, reliability, and GPU scale, designed to handle constant model launches and rapid customer traffic growth. Runware's core focus is on making real-time AI inference accessible and scalable through their global production platform.
