Senior Backend Engineer, Architecture Engineering: Nonlinear Productivity
Build reliable AI-powered automation that removes friction from GitLab’s software development lifecycle. The role requires production experience with agentic or LLM systems, strong distributed-systems judgment, and proficiency in Go, Rust, or Python.
About the job
Responsibilities
- Identify sources of friction across GitLab's software development lifecycle and scope agentic solutions to address them.
- Design and build reliable AI-powered systems using step-by-step workflows, tool use, safety checks, and error recovery.
- Build and maintain evaluation tools that assess agent output for correctness, constraint compliance, and cost.
- Work across GitLab's codebase to address friction wherever it occurs.
- Apply distributed-systems judgment to identify generated code that may fail under concurrency, at scale, or across self-managed, dedicated, and multi-tenant deployments.
- Collaborate with the India-based group by sharing roadmaps, findings, and reusable agent tooling.
- Own a greenfield problem space and help shape proven internal solutions into customer-facing capabilities.
Requirements
- Hands-on experience building agentic or large language model-based systems with multi-step orchestration, tool use, guardrails, and recovery patterns.
- Experience making AI systems reliable in production.
- Ability to work autonomously in unfamiliar codebases and drive solutions through completion.
- Strong distributed-systems knowledge, including coordination, consistency, idempotency, rate limiting, failure modes, and degradation under load.
- Proficiency in Go, Rust, or Python, with the ability to read and modify code in the other languages.
Nice to Have
- Experience shipping autonomous agents that complete real tasks end to end.
- Experience improving build systems, release processes, review workflows, or other software development lifecycle processes.
- Experience working with globally distributed teams, large language model workload costs, or production constraints across on-premises, air-gapped, single-tenant, and software-as-a-service deployments.
Compensation and Benefits
- Flexible paid time off.
- Team member resource groups.
- Equity compensation and employee stock purchase plan.
- Growth and development fund.
- Parental leave.
Skills
Go, Rust, Python, LLMs, AI Agents, Distributed Systems, Agent Orchestration, Guardrails, Idempotency, Rate Limiting, Concurrency, Evaluation Tools
Similar jobs
Backend Engineering jobs
Coinbase
United States
Build and operate high-throughput blockchain infrastructure, APIs, and platform primitives integrating protocols such as Ethereum and Bitcoin with internal services. Requires 5+ years of software engineering experience, distributed-systems expertise, and hands-on crypto infrastructure experience.
Cloudflare
Atlanta, GADesign, build, and operate Cloudflare’s globally distributed cache and reverse-proxy data plane, improving performance, correctness, and resilience across the edge. Requires at least 4 years of production systems experience and proficiency in a systems or backend language.
Hinge Health
San Francisco, CA
Senior backend engineer designing and operating reliable billing and financial systems, APIs, data models, and distributed workflows. The role requires 5+ years of professional software development experience, strong backend expertise, and collaboration across Product, Finance, Operations, and Data.
CommandLink
United StatesSenior individual contributor responsible for designing, building, operating, and improving large-scale backend services, APIs, and telemetry pipelines in Go and Python. The role requires production systems ownership, distributed-systems expertise, incident leadership, mentoring, and technical design leadership.
Fetch
United States
Build and operate backend services, data pipelines, storage, and retrieval systems that provide trusted context to agentic platforms and product applications. The role requires 8+ years of software engineering experience, distributed-systems expertise, cloud infrastructure knowledge, and strong data modeling skills.