Platform Engineer - LLM Inference Infrastructure

Verda; Helsinki; Hybrid; EUR 110,000 - 160,000; Full time

Benefits offered by this job

Cash and equity compensation

Job summary

Verda, a Helsinki-based company building a full-stack AI cloud, seeks a Senior Backend Engineer to develop Go-based backend services and Kubernetes-native applications that support inference offerings. You will collaborate with infra and AI teams to enhance reliability, scalability, and developer experience.

This hands-on role covers design through deployment and production operation, with ownership of technical decisions as the platform scales.

Qualifications

• Design, build and operate production backend services in Go.
• Develop Kubernetes-native apps and automation for platform reliability.
• Create APIs and integrations for inference services and cloud platform.
• Ensure scalability, reliability and maintainability through tests and observability.

Responsibilities

• Design, build and maintain production backend services in Go.
• Develop Kubernetes-native applications for reliable platform operations.
• Build APIs and integrations for inference services and cloud platform.
• Improve performance and reliability through testing, observability, and optimization.
• Collaborate with teams on design decisions and production troubleshooting.

Skills

Go backend

Kubernetes

Distributed systems

PostgreSQL

API design

Observability

Testing & validation

English communication

Tools

Helm

Prometheus

OpenTelemetry

NATS JetStream

Redis/Valkey

Job description

At Verda, we're building a full-stack AI cloud, covering everything from data centers and hardware to our own cloud platform that the world's leading AI teams use to do serious AI work.

We strive to make a positive mark on the world through the infrastructure we build and give leading teams a service they can truly depend on. Headquartered in Helsinki, we operate globally with offices in London and San Francisco.

Join Verda while it’s still being built - not once it’s finished.

About the role

At Verda, we are building the platform that makes LLM inference reliable and accessible on our AI cloud.

As a Senior Backend Engineer, you will develop backend services and Kubernetes-native applications that support our inference offering. You will work closely with infrastructure and AI engineering teams to improve the platform’s reliability, scalability and developer experience.

This is a hands-on role with ownership from design and implementation through deployment and production operation. You will help shape technical decisions as the platform grows.

Your responsibilities

• Design, build and maintain production backend services in Go.

• Develop Kubernetes-native applications and automation for reliable platform operations.

• Build APIs and integrations that support our inference services and wider cloud platform.

• Improve scalability, performance and reliability through testing, observability and operational improvements.

• Collaborate across teams on technical design, delivery and production troubleshooting.

Your key competencies

• Experience designing, shipping and operating production backend services, with the judgment to own work from an initial design through production rollout.

• Strong Go experience. You have shipped and maintained production Go services and are comfortable with concurrency, context propagation, API design and error handling.

• A solid understanding of asynchronous execution, concurrency, HTTP and long-lived connections. You can reason about timeouts, resource limits, cancellation and failure propagation.

• Distributed systems experience, including caching, consistency, retries, idempotency and reliable event processing.

• Strong SQL and relational data modelling skills, including transactions, schema migrations and PostgreSQL.

• Hands-on Kubernetes-native development experience, including controllers or operators, custom resources and reconciliation loops. You understand idempotent reconciliation, desired versus observed state, retries and resource lifecycle handling.

• Experience deploying and troubleshooting services on Kubernetes, including Helm, networking, readiness, configuration and safe rollouts.

• A disciplined approach to validation: meaningful tests, load measurements and failure scenarios, with clear communication about what has and has not been verified.

• Clear written English and the ability to explain design decisions, trade-offs and operational behavior to other teams.

Nice to have

• Rust experience, particularly in asynchronous or network services.

• Experience with API gateways, networking or traffic management.

• Familiarity with LLM API protocols and inference systems such as vLLM, SGLang, NVIDIA Dynamo or llm-d.

• Experience with Valkey/Redis, NATS JetStream or comparable distributed state and messaging systems.

• Experience with reliable event processing or usage metering systems.

• OpenTelemetry, Prometheus and capacity planning for workloads with variable request costs.

• Service discovery, GitOps or deployments across multiple Kubernetes clusters and regions.

• Python experience for integration with existing inference tooling.

Why Verda

• Cash and equity compensation along with various fringe benefits.

• Profitable operations with rapid, sustained growth.

• 40+ nationalities, with 6 different ones on the management team.

• A real chance to make an impact and work alongside world class engineers, researchers, and partners across the global AI ecosystem.

Practicalities

• Work mode: Based in Helsinki, Finland or London, UK or remote in Europe

• Level: Senior

• Employment type: Full time and permanent