SlipstreamJobs tracks this role from the company's public career site. Apply directly on the employer's site.
Mixmax is a revenue-team productivity platform used by thousands of sales and customer teams inside Gmail and CRMs. In 2026, the company rebuilt engineering around AI agents—a small, senior team where engineers focus on deciding what to build, designing systems, directing agents, and owning customer outcomes while agents handle most of the coding.
You will own product and platform projects end to end, from brief to shipped feature, using AI agents as your primary development method. Your responsibilities include:
• Shape the work: Turn briefs into detailed specs with clear user needs, acceptance criteria, technical plans, cost analysis, security considerations, and instrumentation, collaborating with product and design.
• Design systems: Make architectural decisions, keep them simple and scalable, and document decisions that matter.
• Orchestrate agents: Run multiple coding agents in parallel, provide them with appropriate context (skills, rules, repo cards, internal MCP servers), and manage cost and token spend.
• Verify everything: Review agent output critically, write Playwright and unit tests, and own PR and release gates.
• Ship and monitor: Release behind feature flags, set up Datadog monitors and product analytics, use Cleric.ai for production investigation, and confirm features work for users.
• Support rotation: Join the support rotation, handle incidents, and convert recurring problems into new project briefs.
• Improve shared systems: Contribute skills, patterns, and learnings to the shared context repo so future pods move faster.
In your first 90 days, you'll set up your AI-native environment, ship a scoped project with a pod, take a support rotation, and contribute at least one learning or skill back to the shared repo.
The company operates with no fixed feature teams—small pods of 1–3 people (engineer, PM, designer) form around prioritized briefs, ship end to end, and dissolve. Agents are the default build method. Every project follows one contract: a living spec with acceptance criteria, an append-only decision log, a release brief for sales/CS, and an honest retrospective. Verification gates replace handoffs; an agent verifier checks every PR against the spec, and another checks every release on staging. Designs are code—designers ship AI-generated, production-ready prototypes you build against. You have autonomy with accountability: decide how to build, which tools to use, and when to ship behind a flag, with compliance and customer-data rules always applying. The team talks in weeks and scopes down until it hurts, prioritizing outcome over output.
Tech stack: TypeScript and Node.js (Express), MongoDB, AWS (Fargate, Lambda, SQS, EventBridge, DynamoDB), Terraform, React in an Nx/pnpm monorepo, Vitest and Playwright, GitHub Actions, Datadog and Cleric.ai for observability, Linear, and internal MCP servers.
REQUIREMENTS:
• 6+ years building and running production software, with deep backend experience and range across the stack.
• A working AI-native setup you can demonstrate: Claude Code, Codex, Cursor, or similar, with your own skills, rules, MCP servers or agent workflows, and examples of running agents in parallel.
• Strong judgment on agent output—you catch subtle bugs, security issues, and architectural drift, and know when not to trust a green test run.
• Experience designing distributed systems on AWS: event-driven flows, queues, idempotency, failure recovery, and cost optimization.
• Ownership of quality without a QA team: test strategy, CI, observability, feature flags, and incident response.
• Product sense: explain why projects matter to customers, cut scope to essentials, and measure results.
• Clear written communication in English for specs, decision logs, and async updates.
• Comfort with ambiguity and change; you help shape an evolving operating model.
Nice to have:
• Building LLM-powered product features: agents, tool use, MCP servers, evals.
• Building internal agent tooling: PR review bots, sandboxed agents, context services.
• Gmail, Google Workspace, or CRM (Salesforce, HubSpot) integrations.
• SOC 2 or security-conscious engineering in SaaS.
