Careers · Engineering

Senior Agentic Platform Engineer

At VaultSpeed, we build the automation platform that generates data warehouses. Our product generates the Data Vault 2.0 model, meeting customers' business model, and the orchestration flows that load it across a dozen target platforms. It replaces months of hand-written pipeline code with metadata and generation.

  • LocationLithuania
  • TeamEngineering
  • Work setupRemote, hybrid, or office-based
  • Salary€6,000 - €7,500 gross/month

Apply by email Read the role

We're looking for a Senior Engineer to join the Agentic team. The work spans the whole stack: the agents and their skills, the platform services they run on, the infrastructure that runs them for many customers, and the interface people use to work with them. You'll own areas of that system from technical design to release.

This is a role for someone who wants to build AI features that customers rely on in production, as a hands-on engineer in a small team.

What you'll do

  • Build agents and skills. Design, write and improve the agents that ingest sources and generate models and code, and the skills that carry our data modelling knowledge. Decide what belongs in a prompt, a skill, a tool or plain deterministic code.
  • Measure agent quality. Build evaluations and regression suites for agent behaviour, so changes to prompts, models or tools are judged on evidence.
  • Contribute to architecture decisions. Own the design of the features you build, write up technical proposals, and work through the trade-offs with the team.
  • Extend the platform. Work on our layer on top of Omnigent: multi-tenancy and tenant isolation, authentication and organisation management, the MCP tool suite agents use to reach warehouses, the context store and other systems, the agent marketplace, and the LLM gateway that lets customers bring their own model keys.
  • Keep our fork in sync. Regularly merge Omnigent upstream changes into our fork, resolve conflicts with our customisations, and contribute fixes and features back to the open source project.
  • Run agents safely at scale. Work on the sandbox infrastructure where agents execute, built on Kubernetes agent-sandbox: templates, warm pools, persistence, suspend and resume, observability and cost. Ship changes through our GitOps workflow with Argo CD.
  • Investigate and resolve issues. Agents fail in less predictable ways than ordinary code. Reproduce the problem, trace it through logs and model traces, identify the root cause and fix it.
  • Review and release. Review designs and pull requests, support releases, and share what you learn with the team.

What we're looking for

Required:

  • Hands-on experience building with LLMs. Tool calling, structured outputs, context management, and the judgement to know where a model is the right tool and where it isn't. You have shipped LLM-based features to real users, beyond a prototype.
  • Back-end fundamentals. Designing services and APIs, authentication, data modelling and working with databases.
  • Kubernetes and GitOps. Docker, and hands-on experience deploying and debugging services on Kubernetes through a GitOps workflow.
  • Comfortable working in a large codebase you don't own: reading unfamiliar code, understanding upstream design decisions, and resolving non-trivial merge conflicts.
  • Strong analytical thinking. The ability to take a vague symptom, form a hypothesis, test it against evidence, and arrive at a cause rather than a workaround, also when the system involved is non-deterministic.
  • 5+ years of professional software engineering experience, including owning the technical design of significant components through to production.
  • Daily use of AI coding tools such as Claude Code or Cursor.
  • Experience working in a Scrum team: refinement, estimation, code review, and communicating clearly about progress and blockers, across a distributed team
  • Fluent communication in English.

Valuable, but you can learn it here:

  • Agent frameworks and protocols: Model Context Protocol (MCP), the Claude Agent SDK, LangGraph or similar.
  • LLM evaluation and observability tooling, such as MLflow or Langfuse.
  • Graph databases (Neo4j).
  • Multi-tenant SaaS and identity: OIDC, SSO, providers such as WorkOS.
  • Kubernetes agent-sandbox or other sandboxed execution environments.
  • Comfortable making minor front-end changes in the platform UI.
  • Data engineering or data warehousing.
  • Experience maintaining a fork of an active open source project, or contributing to one.

Why VaultSpeed?

  • Build an AI product in a well-defined domain, data modelling and warehouse automation, where agent output can be checked against a real model.
  • Join a new product early, in a small team, where your design decisions shape how the platform grows.
  • Build on open source and contribute back to it.
  • BOwn problems end to end: investigation, design, implementation, evaluation and release.
  • Work remotely, in a team organised around trust and outcomes.

Compensation & Benefits

  • Gross salary €6,000 - €7,500 gross/month, depending on your knowledge, experience, and skills.
  • Choose the way you work: remote, hybrid, or office-based.
  • Continuous learning through training programs and industry conferences.
  • Fully employer-paid private health insurance.
  • A fast-growing, innovative company where your work has a direct impact on customers, products, and business growth.

How we work

We work in Scrum sprints, using Git and Linear. All codebase changes go through pull requests and peer reviews, backed by automated tests and, for agent behaviour, evaluations. Larger technical choices are written up and discussed before they are made, and we show our work to each other at regular Demo Days.

We value engineers who dig into a problem until they understand it, write things down, ask questions early, and leave the codebase better than they found it.

If you're interested in building AI agents for data warehousing, send your resume to hr@vaultspeed.com