Lead Platform Engineer

About Ojin

Ojin is The Human AI Company. We build the infrastructure that makes AI feel human. Our Human Agents deliver natural, lifelike conversations in real time, powered by our proprietary models and blazing-fast APIs on a globally distributed GPU fabric.

We've built award-winning AI experiences for brands including BMW, H&M, and Clinique. Now we're opening that infrastructure up as a platform that will define how the world experiences AI and we're assembling a small, ambitious team of exceptional people to do it.

The Role

At Ojin, the infrastructure underneath our product is what makes it exceptional - real-time AI at scale only works if the systems powering it are built right. This is the person who owns that.

You’ll manage GPU deployments at scale across multiple clouds and regions, architect the systems that make real-time AI possible, and build and own the backend services that sit closest to that infrastructure, so the platform and the product move forward together. You’ll set the technical direction for how we build and scale as the platform grows, and take a leadership role in some of our most important cross-functional work, including driving our compliance and security certifications, where your ability to coordinate across teams matters as much as your technical depth.

You’ll also build and own the backend services that sit closest to the infrastructure, so the platform and the product move forward together.

If you want to own hard problems end-to-end and shape how a fast-moving AI company builds its infrastructure from the inside, this is the role.

What You'll Do

• Manage large-scale deployments of thousands of concurrent GPU servers, with a sharp focus on performance and efficiency
• Develop backend services in TypeScript or Go, such as session routing, platform APIs and scaling logic
• Architect and implement systems for dynamic deployment, routing, and load balancing across multiple clouds and regions
• Create deployment pipelines that are scalable, reliable, and actually a pleasure to work with
• Set technical direction for infrastructure and backend decisions, and raise the bar for how the team builds and operates
• Champion simple, robust tooling: research it, document it, and drive adoption across the team
• Own observability and monitoring, so we always know what’s happening and can move fast when something isn’t right
• Lead our compliance and security certification work, including SOC2 Type II, coordinating across engineering, product and operations to get it done without it becoming a full time job in itself
• Represent Ojin in technical conversations with enterprise clients, and help shape product decisions
• Use AI agents as a core part of your workflow, setting the guardrails and context that let them handle day-to-day work safely, including compliance
• Build software that’s testable, operable and maintainable, and hold that standard across everything we ship

What We're Looking For

• 5+ years of hands-on experience with AWS in production
• Strong proficiency in TypeScript or Go, including building and running backend services and APIs
• Deep knowledge of Infrastructure-as-Code: AWS CDK, Pulumi or Terraform
• Real experience running workloads on at least one other major cloud platform (Azure, GCP, Oracle OCI) or on-premise
• Proven expertise in serverless architectures and security best practices
• Solid understanding of containerisation and Docker in real-world environments
• Experience with globally distributed, low-latency system - this is core to what we do
• Advanced agentic engineering skills: AI agents are part of how you work every day, and you know how to review, challenge and correct what they produce
• Startup experience, and comfort with what that brings: fast decisions, hard problems, and real ownership from day one
• A confident communicator in English, comfortable explaining complex technical decisions to technical and non-technical audiences, and holding your own in team discussions and with enterprise clients
• Ambitious and genuinely excited about what we’re building, with the drive to take it further

Nice To Have:

• Experience with AI/ML workloads and GPU infrastructure
• Experience in AWS CDK specifically
• Background in systems programming or graphics programming
• Experience with real-time media or streaming systems (e.g. video, audio)

Why Work With Us:

• Set technical direction and have real influence over how we build as the platform scales
• Work directly with the founding team with visibility into how the business grows
• A small, talented team where your output is felt immediately
• Remote-friendly within CET ±2 hours, with a Berlin office if you're based locally
• 28 days paid vacation plus 1 mental health day per year
• €900 annual education budget
• Home office equipment provided
• High performance, transparency, humbleness, and pride in our work 

Note: We're not able to offer visa sponsorship or relocation support for this role - you'll need to already be based within CET ±2h and have the right to work where you live.