AI Backend Engineer

Klarity•San Francisco, CA

18h•Onsite

About The Position

We're hiring Backend + Applied AI Engineers to build the core systems that power Klarity's multimodal agents in real enterprise environments. This is a hands-on engineering role at the intersection of distributed systems and applied AI: you'll design and ship backend services that ingest messy real-world data, orchestrate model/agent workflows, enforce enterprise-grade security and deliver reliable outcomes at scale. You'll work closely with product, design, and other engineers to turn ambitious AI capabilities into production-grade features that Fortune 500 enterprises can depend on. We care deeply about engineering fundamentals (correctness, observability, security, performance) and equally about iteration speed - because in this space, only the teams who ship quality products & features at incredible velocity win. You'll be paired with senior engineers who'll accelerate your growth, but you'll own real features from day one - we don't believe in extended bench time.

Requirements

Backend engineer with sharp product judgment - You design and build services, APIs, data models, and infrastructure that are reliable, observable, secure, and fast. You're building strong instincts for architectural tradeoffs and you actively seek feedback on your design decisions. You optimize for outcomes - developer velocity, latency, correctness, uptime - and not just for elegance in the abstract.
Systems thinker - You're developing the muscle to see around corners. While solving today's stated requirements, you anticipate how services will need to evolve - functionally and non-functionally. You design for the future but build for the present, and you ask good questions about why things are built a certain way and push back when complexity isn't justified.
Applied AI builder who ships to production - You're energized by LLMs, multimodal agents, orchestration protocols, and the messy work of making the entire AI stack reliable. You think instinctively in terms of evals, model regression tests, traceability, and exception handling. You've built at least one meaningful AI-powered project - whether production, open-source, or a serious side project - and you understand the gap between a working demo and a reliable system.
AI-native developer across the entire SDLC - You wield tools like Cursor, Claude Code, and Copilot as extensions of your craft. You are extremely confident to run concurrent agents doing your chores reliably. You use AI to generate technical designs, scaffold APIs, draft schemas, write tests, and build migration plans. You're hungry to master these workflows and are already noticeably faster than peers who haven't embraced AI tooling.
Ship with velocity and craft - You find the shortest path to get features into users' hands while obsessing over the details that create trust. You can calibrate the tradeoff between speed and tech debt, and you welcome guidance on where the line is. You believe speed and quality aren't opposites - they happen together when you're thoughtful about how you build.
Bring energy that elevates the entire team - You see gnarly distributed systems challenges as puzzles waiting to be solved. Your optimism, intensity, and passion for craft are contagious. You make everyone around you faster and more ambitious. You also frequently cross-pollinate learnings by seeking and sharing them with the team.
1-3 years shipping production code (or exceptional new grads with strong portfolios)
We do not require a CS or Engineering degree. We care about your ability to ship, your systems thinking, and evidence of strong execution - whether through production work, open-source contributions, research, or high-quality side projects.

Responsibilities

Build the backbone of Klarity's AI platform - Design, experiment, build, test, and deploy the backend services that power everything our users use. You'll own meaningful components of critical infrastructure - shipping features end-to-end with increasing scope and autonomy: from data ingestion and storage to API design, background processing, and deployment architecture.
Turn AI pipelines into resilient workflows - Implement AI orchestration pipelines that hold up under real-world variability. You'll work with structured outputs, tool calling, state management, grounding, and other guardrails to ensure agents behave reliably at scale. You'll start by building and extending evals, adding guardrails, and hardening existing pipelines - rapidly developing the judgment to design new ones.
Design for the future, ship for today - Balance long-term architectural vision with relentless shipping cadence. You'll make pragmatic decisions that keep the codebase healthy and the product moving forward - developing judgment on when to take on deliberate tech debt with the support of senior engineers.
Build for enterprise security and scale - Design least-privilege access, strong tenant isolation, auditability, and secure data handling. You treat trust and safety as core engineering requirements, not afterthoughts. You also design and build systems that scale gracefully as a feature grows from 0 → 1 → 10 → 100. You'll work within established security patterns and contribute to extending them as new use cases arise.
Grow your impact across disciplines - You'll develop fluency across backend, AI, product, and infrastructure by working alongside teammates from each discipline. Turn ambiguous product asks into clean technical specs, and learn to bridge gaps between teams with working prototypes.