Inference.net is hiring a Senior Full-Stack (Frontend-Focused) Engineer
Help us build beautiful, performant web experiences that give users super-powers over our globally distributed LLM inference platform. If you love shipping React apps that feel snappy at planet-scale, we’d love to meet you.
We combine idle GPU capacity from around the world into a single cohesive plane of compute capable of serving models like DeepSeek and Llama 4. At any moment, 5,000+ GPUs and hundreds of terabytes of VRAM are connected to our network.
We’re a small, well-funded team working in-person from downtown San Francisco (hybrid flexibility as needed). Investors include a16z CSX and Multicoin. We’re high-agency, collaborative, and obsessed with craft—whether that’s a distributed scheduler or a pixel-perfect UI.
Own the user experience – design, build, and polish the dashboards, consoles, and customer-facing apps that let users observe, configure, and pay for inference at scale.
Ship end-to-end features – from Figma wireframe to React component to backend API and database migration.
Design a component system in React + Tailwind that supports rapid iteration and a cohesive design language.
Optimize performance – SSR, code-splitting, hydration, and WebSocket-driven real-time updates that hold up under millions of requests per day.
Collaborate across disciplines – work shoulder-to-shoulder with distributed-systems engineers, product designers, and founders to turn complex infrastructure into delightful product.
Level-up the team – lead design reviews, mentor junior engineers, and introduce best practices for testing, accessibility, and observability.
Must-Have
5+ years building production React applications
Deep knowledge of Tailwind CSS & modern CSS architecture
Typescript mastery and strong fundamentals in JS/DOM/APIs
Experience designing REST/JSON or gRPC backends (Node, Go, or similar)
AuthN/AuthZ design (OIDC, JWT)
Product sense: you care about UX details & accessibility
Nice-to-Have
Experience with Tanstack / Next.js
Data-viz libraries (Recharts, Visx, D3)
tRPC experience
Familiarity with GPU or ML tooling dashboards
Comfort debugging perf issues (Lighthouse, Chrome DevTools)
Dev-ops chops: CI/CD, Docker, Terraform
You don’t need to tick every “nice-to-have” box—curiosity and the ability to learn quickly matter more.
Base salary: $120,000 – $180,000
Equity: significant early-stage grant
Benefits: full medical/dental/vision, 401(k) with match, generous PTO, commuter + hardware stipends, daily office lunch
We iterate fast, test in prod (safely!), and celebrate small wins. You’ll demo work twice a week, pair with systems engineers, and ship to users continuously. Most of us are in the office 3–4 days a week; remote candidates considered if time-zone compatible with Pacific hours.
Inference.net is an equal opportunity employer. We value diversity and do not discriminate on the basis of race, color, religion, gender identity, sexual orientation, national origin, veteran status, disability, age, or any other protected status.
Send a short note and a link to something you’ve shipped (code, demo, or Dribbble shots) to [email protected]. We can’t wait to chat!
Job details are sourced from the employer's original posting.
Open job postingAbout the company
Inference.net is building the world's largest distributed GPU cluster. They are seeking a Filmmaker / Storyteller to define the narrative of this endeavor and create compelling content that resonates with users.