Backend Engineer

About the role

Arena Intelligence is seeking a backend engineer to construct the application layer that sits atop its evaluation infrastructure, transforming raw model assessments into reliable, enterprise-grade products. You will design and ship the APIs, services, and data systems that expose Arena's evaluations to customers, working in tight collaboration with infrastructure engineers who manage the underlying runtimes and gateways. The scope spans greenfield development of billing, usage metering, and multi-tenancy systems as well as scaling existing data pipelines and leaderboard backends. You will implement the business logic that translates complex evaluation results into consistent, queryable metrics while ensuring data integrity and performance under load. As an early member of the enterprise team, you will partner directly with researchers and product leadership to turn novel evaluation methodologies into durable, versioned APIs that can be integrated into customer workflows. The environment demands high velocity paired with rigorous engineering standards, requiring comfort with evolving requirements and a bias for shipping robust solutions. This role is ideal for an engineer who thrives on ownership, enjoys debugging intricate distributed interactions, and takes pride in building the foundational systems that make intelligence measurable and repeatable. You will be instrumental in defining the backend architecture that determines how customers interact with Arena's core evaluation capabilities.

Key facts

What you'll do

Architect and implement new backend services in Python and TypeScript to support Arena's evaluation workflows, focusing on scalability, maintainability, and observability.

Design and deliver RESTful and gRPC APIs that enable customers and internal tools to submit evaluations, query results, and manage access to model assessments.

Build data ingestion pipelines that reliably process evaluation outputs, normalize them across different model formats, and store results in performant stores suitable for analytics.

Implement multi-tenant isolation and billing logic, ensuring that metering, subscription tiers, and feature flags are enforced consistently across all services.

Collaborate closely with infrastructure engineers to integrate with container orchestration platforms, service meshes, and API gateways that handle traffic routing and security.

Lead the evolution of the leaderboard backend, optimizing query performance and enabling new dimensions of comparison across evaluated models and datasets.

Partner with research and product teams to translate evaluation experiments into versioned API contracts, enabling reproducibility and longitudinal analysis of model improvements.

Own critical production services end to end, including defining SLIs and SLOs, setting up alerting, and driving improvements in reliability and incident response.

Write comprehensive tests, integration checks, and documentation that allow other engineers to safely extend and modify backend components without degradation.

Investigate and resolve production incidents related to data pipelines, API latency, or tenant isolation, applying root cause analysis to drive long-term fixes.

Evaluate and introduce open source or commercial tools that reduce operational overhead, such as task queues, caching layers, and structured logging systems.

Work with security and compliance stakeholders to ensure that backend services adhere to data handling policies, audit requirements, and access control best practices.

Guide technical decisions through design documents and code reviews, promoting consistency across services and reducing duplicated effort across teams.

Mentor junior engineers by providing code feedback, pairing on tricky problems, and helping establish best practices for testing and deployment.

Requirements

You have a Bachelor's or Master's degree in Computer Science, Engineering, or a closely related technical field, or equivalent practical experience.

You possess 3+ years of professional backend development experience shipping services that handle real traffic and data volumes.

You are proficient in Python and TypeScript, with a strong grasp of asynchronous programming patterns, data serialization, and API design.

You have hands-on experience with at least one relational database such as PostgreSQL, including schema design, indexing strategies, and query optimization.

You understand distributed systems principles, including consistency models, fault tolerance, and idempotent design, and have debugged issues in networked environments.

You are comfortable working with containerized applications and orchestration tools, and you know how services integrate through APIs and message buses.

You have written and maintained production code, including monitoring, logging, and alerting, to ensure services are observable and maintainable.

You demonstrate strong problem-solving skills, breaking down ambiguous requirements into concrete technical tasks and delivering robust backend components.

Nice to have

Experience with large language model pipelines and evaluation frameworks is a significant advantage for understanding the domain.

Familiarity with streaming data platforms or change data capture patterns is beneficial for building responsive data pipelines.

Knowledge of authentication and authorization standards such as OAuth2 or JWT is helpful for securing customer-facing APIs.

Experience contributing to open source projects or publishing reusable libraries demonstrates strong engineering communication.

Practical notes

This role is based in the Bay Area.

The engagement is full time.

Candidates must be authorized to work in the United States without sponsorship for this position.