AI Backend Engineer

Within•San Francisco, CA

About The Position

Within is hiring a Backend and Applied AI Engineer to build core systems powering multimodal agents in real enterprise environments. The role combines distributed systems and applied AI, including backend services for ingesting real-world data, orchestrating model and agent workflows, enforcing enterprise-grade security, and delivering reliable outcomes at scale. The engineer will collaborate with product, design, and engineering teammates to deliver production-grade features for Fortune 500 customers, with emphasis on correctness, observability, security, performance, and rapid iteration. The position offers hands-on ownership of meaningful features and infrastructure from day one, with support and feedback from senior engineers. A computer science or engineering degree is not required; the company values demonstrated ability to ship, systems thinking, and strong execution through production work, open-source contributions, research, or high-quality side projects.

Requirements

1–3 years of experience shipping production code, or be an exceptional new graduate with a strong portfolio.
Ability to design and build reliable, observable, secure, and performant services, APIs, data models, and infrastructure.
Strong systems thinking and developing judgment around architectural tradeoffs, service evolution, and avoiding unjustified complexity.
Experience building at least one meaningful AI-powered project in production, open source, or as a serious side project.
Understanding of the difference between an AI demo and a reliable production system, including the importance of evaluations, model regression tests, traceability, and exception handling.
Comfort using AI development tools such as Cursor, Claude Code, and Copilot across the software development lifecycle.
Ability to use AI tools for technical designs, API scaffolding, schema drafting, test writing, and migration planning, including coordinating concurrent agents.
Ability to ship quickly while maintaining product quality, manage technical debt thoughtfully, and respond to engineering guidance.
Strong collaboration, communication, initiative, and enthusiasm for distributed systems and engineering craft.

Responsibilities

Design, build, test, and deploy backend services that power the Within AI platform, including data ingestion and storage, APIs, background processing, and deployment architecture.
Own and ship meaningful components of critical infrastructure and features end to end, with increasing scope and autonomy.
Implement resilient AI orchestration pipelines using structured outputs, tool calling, state management, grounding, and guardrails.
Build and extend evaluations, add guardrails, and harden existing AI pipelines before taking on the design of new pipelines.
Balance long-term architectural needs with a rapid shipping cadence and make pragmatic decisions about technical debt.
Design for enterprise security and scale, including least-privilege access, tenant isolation, auditability, and secure data handling.
Help systems scale as features grow from early implementation to broad adoption, while following and extending established security patterns.
Translate ambiguous product requests into technical specifications and build prototypes that help bridge teams.
Collaborate with backend, AI, product, design, and infrastructure teammates.