About RELAI
RELAI is building the infrastructure to make AI agents reliable in production. We help enterprises design, evaluate, and optimize AI agents, turning brittle prototypes into robust, scalable workflows that actually work in real-world environments.
We operate at the intersection of:
- AI agent design
- Evaluation and optimization
- Enterprise deployment
- Developer and enterprise tooling
Our ambition is to define how AI systems are built in production.
The Role
We are hiring a senior Full-Stack Engineer with 5+ years of experience to design, ship, and harden the product and platform experiences that make AI agents reliable in real-world environments.
You will:
- Be a core part of the full-stack foundation of RELAI’s platform; the bridge between AI product ideas and production reality.
- Be a key driver of reliability, enterprise readiness, and product evolution.
- Build and maintain full-stack product features for agent workflows, evaluation pipelines, optimization tools, and enterprise platform capabilities.
- Build and integrate Django-based backend services and APIs, async workflows using Celery, and AI/LLM integrations.
- Work closely with product and AI teams to turn new agent capabilities into production-ready user experiences and backend systems.
- Own features end-to-end, from local development to deployed enterprise environments.
- Help shape backend API design, frontend architecture, developer workflows, and deployment practices as the platform scales.
- Design reliable data-heavy interfaces for evaluations, benchmarks, reports, charts, tables, editors, and workflow visualization.
Who You Are
You are a strong full-stack engineer with deep experience building production web applications, backend services, and reliable developer workflows.
You care about product quality, system correctness, frontend craft, API design, and operational reliability. You are comfortable working close to modern AI infrastructure and turning fast-moving product ideas into dependable systems.
Core requirements
- Strong proficiency in Python and backend web frameworks, especially Django
- Experience designing, building, and consuming production APIs
- Solid understanding of async systems, background jobs, message brokers, and caching systems such as Celery, Redis, and Kafka
- Experience with observability, error tracking, and production debugging, including tools such as Sentry
- Solid understanding of Docker, Docker Compose, and production deployment workflows
- Proficiency in TypeScript and React, enabling you to independently ship features end-to-end
- Proficient in using coding agents like Claude Code/Codex and working in a fast-paced environment with continuous deployment
Experience we value
- Kubernetes/Kustomize for deployments
- Building and integrating with cloud-native services on GCP, AWS, or Azure
- Strong product sense and ability to make pragmatic UX decisions without waiting for detailed specs
- Experience with modern React ecosystems and tooling (e.g., Vite, the TanStack suite)
- Experience with component systems and modern CSS architecture
- Experience in AI infrastructure, evals, agents, observability, or enterprise developer tools
The Bar at RELAI
We are explicit about this: the bar to work at RELAI is extremely high. We are building a small team of people who:
- Operate with extreme ownership
- Think in systems, not features
- Can go from 0 to production with customers
- Care about both frontend quality and backend correctness
- Raise the standard for everyone around them
You should expect:
- High intensity
- High autonomy
- High expectations
- Broad ownership across product, platform, and infrastructure
Why Join
- Work directly on one of the hardest problems in AI today: reliability in production
- Build the product interfaces and backend systems enterprises will use to evaluate and operate AI agents
- Be at the center of product, AI, frontend, backend, and infrastructure
- Join early and have outsized impact on the company
Compensation
- Competitive salary
- Meaningful equity