Staff AI Systems Engineer — Agentic Platforms

Kindo • Los Angeles, CA

12h • $210,000 - $260,000 • Hybrid

About The Position

The role of the software engineer is changing. Autonomous agents can now execute real workflows, operate infrastructure, and improve over time. The hard problems are shifting from model demos to production systems: orchestration, memory, reliability, control, and security.
OpenAI acquired OpenClaw. Meta paid $2B for Manus. The agent platform layer is becoming one of the most important layers in the stack.
At Kindo, we’re already there. Our platform runs autonomous agents in production at real enterprises, automating DevOps and SecOps workflows with real permissions, real consequences, and real reliability requirements.
About Kindo
Kindo is an agent automation platform for DevOps and SecOps teams. We help organizations automate high-friction operational work using autonomous agents that run reliably, securely, and at scale. Our platform supports deployment on-prem, in hybrid environments, or in the cloud, with enterprise-grade security controls from day one.
We’re a small, highly technical team with strong customer traction and real enterprise revenue. Engineers have direct ownership over critical systems and shape how the platform evolves.
The Role
You will define, build, and evolve foundational systems that enable autonomous agents to operate reliably in production. This is applied systems engineering with AI at the center, not ML research and not chatbot wrappers. You’ll work on agent execution frameworks, retrieval and memory systems, multi-model execution, and secure tool-calling integrations that interact with real enterprise environments.
This role also requires invention. Many of the patterns for agentic systems are still emerging. You’ll explore new approaches, prototype quickly, and turn what works into durable platform foundations. You’ll identify high-leverage architectural improvements, abstractions, and guardrails that expand what the platform can do while keeping it reliable, secure, observable, and maintainable under real-world conditions.
Staff engineers at Kindo are builders and inventors with strong architectural judgment. You help define both what we build next and which approaches become the system’s durable defaults.
What You’ll Build
Agent execution systems, including autonomous task loops, scheduling, triggers, and control planes
Retrieval and memory architectures, including context management, long-term memory, and structured memory
Multi-model routing and orchestration across providers, balancing quality, latency, cost, and failure modes
Tool-calling and integration frameworks for safe interaction with external services and enterprise environments
Reliability, security, and operability foundations, including evaluation, observability, failure isolation, and recovery paths
Core platform abstractions and architectural patterns that make new agent capabilities easier to build safely
How You Build
AI is a first-class tool in how we engineer. You use AI across design, prototyping, implementation, testing, debugging, and incident response, and you continuously refine workflows that increase leverage without sacrificing quality. You develop pragmatic guardrails, verification strategies, and architectural boundaries to minimize slop, reduce risk, and keep systems safe as autonomy increases.
You also push the team’s defaults forward through better patterns, reusable workflows, and clearer architectural primitives, so the whole organization builds faster with fewer failure modes.
What We’re Looking For
We care far more about what you’ve built than what’s on your resume.
You:

Requirements

• Have deep experience building and operating complex backend or distributed systems in production
• Have built LLM-powered or AI-native systems beyond demos, with real users, real constraints, and real failure modes
• Have strong architectural judgment around reliability, security, observability, and system evolution
• Have invented or introduced abstractions, workflows, or architectural approaches that materially improved system capability or engineering effectiveness
• Are comfortable operating in ambiguous frontier areas and validating ideas through rapid iteration
• Use AI as a core part of your development workflow, not as an occasional convenience
• Operate with high ownership and take systems end-to-end, including long-term evolution
• TypeScript required, Python strongly preferred
• Strong SQL proficiency
• Experience with production infrastructure; Docker/Kubernetes experience is a plus
• Familiarity with enterprise security patterns is a plus
• Domain familiarity with DevOps, SecOps, or infrastructure automation is a plus

Responsibilities

• Define, build, and evolve foundational systems that enable autonomous agents to operate reliably in production.
• Work on agent execution frameworks, retrieval and memory systems, multi-model execution, and secure tool-calling integrations that interact with real enterprise environments.
• Explore new approaches, prototype quickly, and turn what works into durable platform foundations.
• Identify high-leverage architectural improvements, abstractions, and guardrails that expand what the platform can do while keeping it reliable, secure, observable, and maintainable under real-world conditions.
• Use AI across design, prototyping, implementation, testing, debugging, and incident response, and you continuously refine workflows that increase leverage without sacrificing quality.
• Develop pragmatic guardrails, verification strategies, and architectural boundaries to minimize slop, reduce risk, and keep systems safe as autonomy increases.
• Push the team’s defaults forward through better patterns, reusable workflows, and clearer architectural primitives, so the whole organization builds faster with fewer failure modes.

What This Job Offers

• Job Type: Full-time
• Career Level: Mid Level
• Education Level: No Education Listed