Senior Backend Engineer (Autonomous Defense)

Horizon3; United States; Remote; USD 150,000 - 210,000; Full time

Benefits offered by this job

Growth opportunities

Innovation-driven culture

Flexible remote work

Inclusive and diverse team

Job summary

Horizon3 seeks a Senior Backend Engineer for the Defensive Agent platform. You will own the agent execution runtime, the tool layer, and the observability that makes agent behavior debuggable across thousands of tenants.

You will work with AI researchers to build a safe, shippable substrate rather than tuning prompts. The role emphasizes durable workflows, per-tenant security, a registry with versioning, and integration with third-party security control planes.

Qualifications

• 7+ yrs professional software engineering experience with OO or functional languages.
• Expert proficiency in SQL and relational/graph databases.
• Track record of shipping and operating production services with on-call ownership.
• Experience designing distributed systems with asynchronous workflows, retries, idempotency, and partial failure.
• Experience building apps on AWS/Azure/GCP with Docker and Kubernetes.
• Experience with durable execution/workflow engines (Temporal) or equivalent checkpointing.
• Experience building agentic or LLM-backed systems in production.
• Experience multi-tenant platforms with strong isolation and short-lived credentials.
• Familiarity with security control planes and APIs (EDR, firewalls, SIEM, IAM).
• Experience GraphQL backends and observability tooling (Datadog, Prometheus, Grafana).
• Awareness of prompt injection and untrusted data handling.

Responsibilities

• Own the agent execution runtime, including durable, long-running workflows with checkpointing and timeouts.
• Design and implement the tool layer and registry with per-tenant enablement and server-side authorization.
• Build a connector framework for security control planes (EDR, firewall, IAM) and audit trails.
• Develop ETL/GraphQL capabilities for agent context, run history, and remediation state.
• Instrument systems with distributed tracing and cost/token accounting for tenant isolation.

Skills

Python

Go

Scala

TypeScript

C++

SQL

GraphQL

Distributed systems

Cloud platforms

Docker

Kubernetes

Temporal

Multi-tenant

Security awareness

Education

Bachelor's degree in CS/CE or related field

Tools

PostgreSQL

Neo4j

Datadog

Prometheus

Grafana

Temporal

GraphQL tooling

Job description

• As a Senior Backend Engineer on the Defensive Agent team, you’ll build the platform that NodeZero’s defensive agents run on. Our AI researchers define what these agents should reason about, you build the systems that make that work in production, across thousands of customer tenants, without breaking anything
• That means real distributed systems problems, not glue code. They execute inside customer environments under tight isolation, credential, and egress constraints
• And when an agent proposes a change in production, the platform has to be able to simulate it, stage it, gate it on approval, roll it back, and prove after the fact exactly what happened and on whose authority
• This is a platform role. You’ll own the runtime, the tool layer, the orchestration, the connector framework, and the observability that makes agent behavior debuggable
• You’ll work closely with our AI researchers, but you are not being hired to tune prompts — you are being hired to build the substrate that makes their work shippable and safe
• Build and own the agent execution runtime: durable, resumable, long-running workflows with checkpointing, idempotent steps, cancellation, and timeouts at both the step and run level
• Design and implement the tool layer that agents act through — a registry with versioning, schema validation, per-tenant enablement, and authorization enforced server-side rather than by the model
• Build the connector framework for third-party security control planes (EDR, firewall, identity, SIEM, cloud IAM)
• Implement the safe-change pipeline: dry-run and simulation, blast-radius classification, approval gates for high-impact actions, staged rollout, rollback, and an immutable per-tenant audit trail
• Extend NodeZero’s tenant isolation model to agents that take write actions, covering execution boundaries, egress control, quotas, and cross-tenant leakage in caches, indexes, and logs
• Develop core product features in ETL and GraphQL to support data processing and retrieval for agent context, run history, and remediation state
• Build the ETL pipelines that turn pentest and remediation outcomes into the datasets our researchers train and evaluate against
• Instrument everything. Distributed tracing across an agent run, cost and token accounting per tenant, and the tooling to answer “why did the agent do that” without guessing
• Partner with AI researchers, attack engineers, and product to take capabilities from prototype to production, and feed platform constraints back into research direction early rather than late

Benefits

• Growth Opportunities: Be part of a dynamic and growing team with numerous career advancement opportunities
• Innovation-Driven Culture: Work in a collaborative environment that encourages creativity and out-of-the-box thinking
• Flexible Work Environment: Enjoy the convenience and work-life balance that comes with remote work
• Inclusive and Diverse Team: We value diversity and promote an inclusive culture where everyone can thrive

7+ yrs professional software engineering experience using modern object-oriented or functional languages (Python, Go, Scala, C++, TypeScript, etc)Expert proficiency in SQLBachelor’s Degree in Computer Science, Computer Engineering or related fieldA track record of shipping and operating production services, including on-call ownershipDemonstrated experience designing and operating distributed systems in production: asynchronous workflows, queues, retries, idempotency, and partial failureExperience building applications on cloud computing platforms such as AWS, Azure, GCP, using container technologies such as Docker and KubernetesExperience with a durable execution (such as Temporal) or workflow engine or having built equivalent checkpointing yourselfExperience building agentic or LLM-backed systems in productionExperience building multi-tenant platforms with hard isolation requirements, workload identity, and short-lived credential brokeringExperience integrating a long tail of third-party APIs behind a normalized abstractionFamiliarity with security control planes and their APIs — EDR (CrowdStrike, SentinelOne, Microsoft Defender), firewalls, SIEM, cloud IAMExperience with database architectures including relational (PostgreSQL) and graph (Neo4j), and experience building GraphQL backendsExperience with observability tooling (Datadog, Prometheus, Grafana) and distributed tracingAwareness of prompt injection and untrusted-input handling in systems where an agent consumes data from the environment it operates in