Software Engineer - AI Tooling Infrastructure

Jobgether; South Africa; Remote; ZAR 900,000 - 1,300,000; Full time

Benefits offered by this job

Fully Remote

Co-working Allowance

Equity Ownership

Tech Allowance

Health Insurance

Annual Off-sites

Flexible Schedule

Professional Development

Global Collaboration

Job summary

Jobgether is seeking a Software Engineer – AI Tooling Infrastructure for a partner company based in South Africa. You will build and operate backend services powering AI-driven developer tools, including MCP servers, agent skills, and AI assistants.

You will own service architecture, implement SLOs, and collaborate across platform, SRE, authentication, billing, and edge teams. You will troubleshoot production systems, design secure auth flows, and contribute to scalable infrastructure in a

Qualifications

• 5+ years of experience building, deploying, and operating production backend services.
• Proficient in TypeScript or Go, with working knowledge of the other language.
• Experience designing and maintaining APIs with versioning and rate limiting.
• Strong understanding of OAuth, OIDC, JWT, and API authorization.
• Good knowledge of PostgreSQL and relational databases.
• Experience with CI/CD, Docker, containerised deployments, and IaC.
• Ability to troubleshoot distributed systems using metrics, logs, and traces.
• Excellent written and verbal communication in distributed teams.
• Ability to navigate ambiguity and deliver solutions in fast-paced environments.
• Deep expertise in APIs/Auth, Production Operations, or Gateways/Distributed Systems.

Responsibilities

• Build, deploy, operate, and scale production backend services for AI-powered tools.
• Own service architecture and deployment processes for reliability and scalability.
• Define and monitor SLOs, error budgets, and improvements with SRE teams.
• Participate in on-call rotations and incident response, write runbooks and reports.
• Manage operational support and address recurring issues with long-term fixes.
• Design authentication systems for AI agents and machine clients (OAuth, tokens).
• Establish observability via metrics, tracing, logging, dashboards, and alerts.
• Manage AI agent traffic with rate limits, capacity controls, and fault handling.
• Collaborate with Platform, SRE, Authentication, Billing, and Edge Functions teams.
• Contribute to AI tooling infra to keep reliability, security, performance at the core.

Skills

TypeScript/Go

APIs & Auth

Distributed systems

Communication

On-call experience

Security awareness

Tools

Docker

Kubernetes

OpenTelemetry

Grafana

Job description

This position is listed on behalf of a partner company, who manages all applications and next steps. Our partner is looking for a Software Engineer – AI Tooling Infrastructure based in South Africa.

We are looking for an experienced Software Engineer to build, operate, and scale the backend infrastructure powering innovative AI-driven developer tools. In this role, you will take ownership of production services, including infrastructure supporting AI agents, developer assistants, and Model Context Protocol (MCP) integrations. You will focus on ensuring reliability, security, performance, and observability in an environment where AI-driven traffic introduces unique infrastructure challenges. Working closely with platform, security, and infrastructure teams, you will help shape scalable architectures and improve operational excellence. This is a hands‑on engineering position offering significant ownership over systems running in production. You will join a globally distributed, asynchronous engineering environment that values autonomy, open-source development, and continuous improvement.

Accountabilities:

• Build, deploy, operate, and scale production backend services supporting AI‑powered developer tools, including MCP servers, agent skills, and AI assistants.
• Own service architecture and infrastructure decisions, improving system reliability, maintainability, scalability, and deployment processes.
• Define and monitor service reliability objectives (SLOs), track error budgets, and prioritize improvements in collaboration with Site Reliability Engineering (SRE) teams.
• Participate in the team's on‑call rotation, investigate production incidents, coordinate resolutions, and develop incident reports, runbooks, and preventive solutions.
• Manage operational support requests and identify recurring issues that can be addressed through long‑term engineering improvements.
• Design and maintain authentication and authorization systems for AI agents and machine clients, including OAuth applications, scoped tokens, permissions, and secure access management.
• Establish and maintain comprehensive observability through metrics, distributed tracing, logging, dashboards, and alerting systems.
• Manage AI agent traffic, implementing rate limits, capacity controls, cost safeguards, and mechanisms to handle dependency failures and unexpected traffic spikes.
• Collaborate with Platform, SRE, Authentication, Billing, and Edge Functions teams to improve shared infrastructure, release processes, security, and operational practices.
• Contribute to the development of AI tooling infrastructure, ensuring that reliability, security, and performance remain central to engineering decisions.

Requirements:

• At least 5 years of experience building, deploying, and operating production backend services, including participation in on‑call rotations.
• Strong programming skills in TypeScript or Go, with practical working knowledge of the other language.
• Proven experience designing and maintaining APIs, including versioning, error handling, rate limiting, and backward compatibility.
• Strong understanding of OAuth, OpenID Connect (OIDC), JWT, and API authorization, with the ability to troubleshoot authentication and permission issues in production environments.
• Good knowledge of PostgreSQL and relational database systems.
• Experience with CI/CD pipelines, Docker, containerised deployments, and Infrastructure as Code (IaC).
• Ability to troubleshoot distributed systems using metrics, logs, and traces to identify performance bottlenecks and service failures.
• Strong written and verbal communication skills, with the ability to collaborate across teams and work effectively in globally distributed, asynchronous environments.
• Adaptability, ownership, and the ability to navigate ambiguity while delivering solutions in fast‑paced engineering environments.
• Deep expertise in at least one of the following areas:
  • APIs and Authentication: Experience designing permission models, token scopes, and OAuth flows for third‑party integrations or machine clients, including safely migrating authentication systems without disrupting existing users.
  • Production Operations: Hands‑on experience managing production services, participating in on‑call rotations, developing alerts and runbooks, implementing SLOs, and improving system reliability.
  • Gateways and Distributed Systems: Experience building or operating proxies, gateways, or distributed services, troubleshooting retries, partial failures, upstream outages, and making appropriate fail‑open or fail‑closed decisions under degraded conditions.

Nice to have:

• Experience with AI agent tooling, Model Context Protocol (MCP), or infrastructure serving AI agents and LLM clients.
• Experience extracting services from larger codebases while maintaining compatibility with existing integrations.
• Familiarity with observability platforms such as Grafana or OpenTelemetry, or log flare, …
• Contributions to open‑source projects, particularly within the Node.js, Go, TypeScript, or API tooling ecosystems.

Benefits:

• Fully Remote: Work from anywhere in the world, with no office attendance requirements.
• Co‑working Allowance: Access to a WeWork membership or co‑working budget to support your preferred working environment.
• Equity Ownership: Employee Stock Option Plan (ESOP), giving every team member an opportunity to share in the company's long‑term growth.
• Technology Allowance: Dedicated budget for professional equipment, including laptops, monitors, headphones, and other work essentials.
• Health Insurance: 100% health insurance coverage for employees and 80% coverage for dependents, regardless of location.
• Annual Company Off‑sites: Opportunities to connect and collaborate with colleagues during a company‑wide gathering in a different city each year.
• Flexible Working Arrangements: Asynchronous work culture with flexibility to organise your schedule and manage your responsibilities independently.
• Professional Development: Annual learning and education allowance for courses, books, conferences, and other career development opportunities.
• Global Collaboration: Join an international, remote‑first engineering team working across more than 60 countries and 20 languages.

How Jobgether works:

We use an AI‑powered matching process to ensure your application is reviewed quickly, objectively, and fairly against the role's core requirements. Our system identifies the top‑fitting candidates, and this shortlist is then shared directly with the hiring company. The final decision and next steps (interviews, assessments) are managed by their internal team.

We appreciate your interest and wish you the best!

Data Privacy Notice: By submitting your application, you acknowledge that Jobgether will process your personal data to evaluate your candidacy and share relevant information with the hiring employer. This processing is based on legitimate interest and pre‑contractual measures under applicable data protection laws (including GDPR). You may exercise your rights (access, rectification, erasure, objection) at any time.