SlipstreamJobs tracks this role from the company's public career site. Apply directly on the employer's site.
Culture Amp is the world's leading employee experience platform, serving 25 million employees across 6,000+ companies. The company is backed by leading venture capital and has offices in the US, UK, Germany, and Australia.
You will be one of the founding members of a small, high-ownership team building Culture Amp's Agent Hub—a central technical capability for designing, shipping, and governing autonomous agents across the business. This is genuinely greenfield work: you'll help define the architecture, engineering patterns, operating model, and guardrails that make agentic systems useful, secure, observable, and safe to run in production.
The Hub functions as a central enablement platform: setting standards, building shared capabilities, and helping teams across the business move from experimentation to governed, production-ready agents and workflows. You'll work closely with AI champions across the organization, turning ambiguous friction into practical solutions while creating patterns that enable teams to build and operate AI-enabled workflows independently.
Key responsibilities include:
- Setting technical direction for foundational Agent Hub capabilities: agent execution, orchestration, MCP tools, identity, context, knowledge, evaluation, and operational visibility
- Designing, building, and operating autonomous agents, workflows, and integrations for internal use cases
- Building reusable MCP servers and tool patterns with clear schemas, credential brokering, identity-aware access, and auditable interactions
- Shaping the knowledge and context layer that grounds agents in organization-specific information using document retrieval, vector search, knowledge graphs, and semantic models
- Establishing engineering practices that move solutions from experimentation to managed services: secure deployment, testing, evaluation, observability, cost awareness, and reliability
- Partnering with teams across the business to identify high-value problems and deliver solutions people actually adopt
- Applying and evolving the agent registry, risk framework, and governance patterns
- Raising capability through coaching, architecture guidance, reusable patterns, documentation, and playbooks
You'll work from the Melbourne office an average of 2 days per week, with flexibility for remote work.
REQUIREMENTS:
- Strong backend engineering skills in TypeScript and/or Python, including APIs, testing, service design, and building production systems or integrations end to end
- Hands-on experience delivering and operating cloud-native solutions in AWS, with strong understanding of security, identity, permissions, secrets, and reliability in production
- Practical experience with AI agents, Claude or similar tooling, MCP or comparable integration patterns, and orchestration across single-agent, multi-agent, workflow, and human-in-the-loop systems
- Working knowledge of agent platforms and runtime concerns: tool permissions, identity propagation, session state, token and time budgets, retries, evaluation, tracing, cost attribution, and auditability
- Experience designing knowledge or memory architectures, including vector or graph-based retrieval, with judgment to choose between build, buy, configure, workflow, and agentic approaches
- Track record of taking ambiguous, unscoped problems from discovery through to shipped and governed solutions, earning stakeholder influence through delivery
- Ability to define platform boundaries and self-service patterns so other teams can move independently without compromising security or operational quality
- Energized by building from zero and defining patterns rather than inheriting them
- Comfortable holding ambiguity, making decisions with incomplete information, and iterating in the open
- Systems thinker who can move between architecture, implementation, operations, and human behaviors needed for adoption
- Pragmatic about hype: excited by autonomous agents, MCP, and knowledge graphs, but focused on measurable value and safe operation at scale
- Generous, team-first collaborator who shares context freely and lifts people around you
