Most engineering teams have added AI to their workflow. A few have rebuilt their workflow around it. We are moving to the second group, and we are hiring engineers to build it with us.
This is not a role where you build LLM products. This is a role where you build our product with agents.
You will work inside a real, high-traffic production codebase: the platform that 2,000+ brands use to engage customers across channels, processing 2.2 billion requests and delivering nearly 2 billion notifications every day. You will plan, implement, test, review, debug and ship features with coding agents doing most of the writing, while you set the intent and own the outcome.
You are not expected to arrive with a company-wide standard in your head. You are expected to already work this way every day, and to leave the team with better prompts, skills, agents and guardrails than it had before you.
If your first reaction to a repetitive workflow is "this should be an agent," we should probably talk.
Why this role existsWe looked at how our engineers work today. Some of them use AI to finish a line of code faster. That is autocomplete, and it is not what we mean.
We mean the full loop: you scope a change, an agent reads the codebase and writes a plan, you correct the plan, the agent implements across many files, runs the tests, fixes what it broke, and opens a pull request. You review the output like a senior engineer reviews a junior — because that is exactly what it is.
Some people already work like this every day. We want more of them on the team, and we want them building the tooling that makes it easy for everyone else.
What You Will Do
- Ship with agents. Claude Code first, plus Codex, Cursor, Copilot or whatever earns its place — your main tool across planning, implementation, testing, debugging, refactoring, documentation and review. Real features in production, with the quality bar you would hold for hand-written code.
- Own the output. Treat what the agent writes as untrusted until you have reviewed it: hallucinations, wrong assumptions, hardcoded secrets, missing validation, injection-prone patterns. Run it, confirm it works, iterate. For authentication, authorization, cryptography and session handling, use our standard implementation rather than the model's invention.
- Fix the context, not the prompt. Keep CLAUDE.md, coding standards, architecture notes and module dependencies current so the agent gets it right the first time. Feed SAST (Static Application Security Testing) and dependency findings back with call path and data flow, so it writes a real patch instead of a suppression.
- Build team-level tooling. Prompts, skills, sub-agents and MCP (Model Context Protocol) integrations for the work that keeps coming back, plus guardrails that keep agents in bounds: architectural limits, forbidden patterns, off-limits folders. Keep the context lean and watch token cost.
- Use agents across the whole lifecycle, not just for code. Integration tests and coverage gap analysis, regression tests generated from real production incidents, root-cause analysis with logs and traces pulled in, ADRs (Architecture Decision Record) and runbooks drafted with AI and checked by you.
- Review AI-assisted work well. Run context-aware AI review on your own diffs, separate true positives from false positives, and turn recurring false positives or escaped bugs into rules the team keeps.
- Share what works. Show your setup to the team, review other people's AI-assisted pull requests, and get at least one thing you built adopted beyond your own repo.
What You Will Need
- Daily use of coding agents on real work. Not a course, not a demo. Code with users, where the agent did a large share of the writing and you owned the result.
- At least one project you can walk us through end to end with these tools: what you delegated, what you kept, where it failed you, and how you caught it.
- Agentic experience: tool and function calling, multi-step workflows, state, error recovery, human-in-the-loop.
- Context discipline. You can show how you set an agent up to succeed — project files, standards, examples, scoped tasks — and how that cut your rework.
- Solid engineering fundamentals. Clean code, testing, error handling, security, performance. Agents make weak fundamentals more expensive, not less.
- The judgment to know when the agent is wrong. Speed is easy to fake. Judgment is not, and it is what we will test.
- Willingness to share it. You do not need to have run a training program. You do need to be the kind of person who shows a teammate the setup instead of keeping it.
- Team-level tooling you built and other people used: shared skills, sub-agents, MCP servers, slash commands, or a review or test agent running in CI (Continuous Integration).
- Security habits around agents: forbidden patterns, least privilege on the tools and credentials an agent can reach, secrets kept out of AI context, AI-suggested packages verified before they are merged.
- Test and debugging depth with AI: coverage gap analysis, regression tests written from production incidents, root-cause work using observability data.
- LLM work: prompt engineering, agent SDKs, or orchestration frameworks such as Strands Agents, LangChain or LlamaIndex.
- Agentic patterns beyond the basics: RAG, MCP, skills, hooks, plugins.
- Experience designing scalable, highly available systems, ideally in Go.
- Curiosity about how these systems actually work under the hood: benchmarking them, breaking them, improving them. On seniority
Language is not a filter. Go and PHP/Laravel are preferred because that is what we run; Python, TypeScript or anything else is fine if the rest is there.
Nice to haveWe are open on seniority. Mid-level and senior candidates are both evaluated, and your level comes from what you have shipped, not from the number on your CV. The one thing we do not flex on: agents are already how you work, not something you are planning to try.
What We Offer
- Enjoy a monthly meal allowance designed to enhance your daily routine
- Access comprehensive private health insurance
- Find your people with yoga classes, running and cycling clubs, and nutrition workshops
- Feed your curiosity with access to Spotify, LinkedIn Learning, Blinkist, MasterClass, Neoskola, and CloudGuru
- Level up with internal trainings covering AI fundamentals, coding, foreign languages, and a wide range of personal development skills
- Be part of a diverse team that’s as global as it gets — where every voice is heard and 50+ nationalities build together
- Become a Shareowner through our eligibility-based “ESOP” and own a piece of what you build
- Help build the team you want to work with and enjoy rewarding referral bonuses
- Opportunities to give back to your community through volunteering and purpose-driven social impact projects
- From global retreats to team-building activities, expect year-round events that turn into lifelong memories
Skills Required
- Daily use of coding agents on real production work
- At least one end-to-end project demonstrating coding-agent usage
- Experience with tool and function calling, multi-step workflows, state, error recovery, and human-in-the-loop systems
- Ability to provide effective agent context through project files, standards, examples, and scoped tasks
- Solid engineering fundamentals including clean code, testing, error handling, security, and performance
- Judgment to identify incorrect or unsafe agent-generated output
- Willingness to share agent setups and practices with teammates
- Team-level agent tooling used by other people
- Security practices for agents, tools, credentials, secrets, and AI-suggested packages
- AI-assisted testing, coverage analysis, regression testing, and root-cause analysis using observability data
- Prompt engineering, agent SDKs, or orchestration frameworks such as Strands Agents, LangChain, or LlamaIndex
- Experience with RAG, MCP, skills, hooks, or plugins
- Experience designing scalable, highly available systems, ideally in Go
- Curiosity about benchmarking, breaking, and improving agentic systems
Insider One Compensation & Benefits Highlights
The following summarizes recurring compensation and benefits themes identified from responses generated by popular LLMs to common candidate questions about Insider One and has not been reviewed or approved by Insider One.
-
Fair & Transparent Compensation — Pay sentiment trends generally positive overall, with pay described as competitive in some roles and markets. Recent role-specific ranges and compensation benchmarks suggest market-aligned pay bands in several functions.
-
Strong & Reliable Incentives — Bonus structures and performance-linked earnings potential appear to meaningfully increase total compensation, particularly in commercial roles. Variable pay and commission mechanics are portrayed as providing upside when targets are achieved.
-
Leave & Time Off Breadth — Time-off policies are described as generous, including an unlimited PTO approach and in some cases additional holiday time. Flexible working hours also contribute to perceived time-off and flexibility value.
Insider One Insights
What We Do
Insider One is the #1 platform that brings everything marketing and customer engagement teams need in one place so they can reach their peak potential and become unstoppable. With AI at its core and an integrated Customer Data Platform (CDP), Insider One unites data, personalization, and journey orchestration across the most extensive set of natively supported channels, including WhatsApp, SMS, Email, Web, App, and Site Search. Insider One provides the ultimate vendor experience, proven in fifteen industries and more than 30 countries for more than a decade, to help teams be first, be focused, and be progressive, redefining what it means to lead in customer engagement. Trusted by 2,000+ customers, including some of the world’s most loved brands like Samsung, L’Oréal, Unilever, Allianz, ING Group, Toyota, Singapore Airlines, and GAP, to accelerate growth, build customer love, and become a market leader. Loved by customers, recognized by analysts, Insider One is the only vendor recognized as the #1 leader in all the capabilities marketing and customer engagement teams need, including AI, Customer Data Management, Cross-Channel Journey Orchestration, and Personalization, offering brands unrivaled product excellence within a single consolidated platform. Accolades include: - Leader in the IDC MarketScape: Worldwide AI-Enabled Marketing Platforms for Enterprise Companies 2025 - Leader in the Gartner Magic Quadrant for Personalization Engines, 2025 - #1 Customer Choice: 2025 Gartner Voice of the Customer for Personalization Engines - Leader in the Forrester Wave for Experience Optimization Platforms, Q4 2024 - The Gartner Customers’ Choice for Multichannel Marketing Hubs in 2025 - The #1 G2 Leader in 11 categories, including CDP, Personalization Engines, Mobile Marketing, Customer Journey Analytics, SMS Marketing, WhatsApp Marketing, eCommerce Search, and eCommerce Personalization, with a perfect 100/100 user satisfaction score.
