Are you a Prompt Engineer who’s just as comfortable shipping production-grade LLM pipelines as crafting the perfect prompt? Join us in building AI systems that don’t just sit in a notebook, but actively power teams across Malta and Europe.
We’re looking for someone with hands-on experience in:
- Prompt design and optimisation – crafting, testing and iterating prompts for accuracy, consistency and cost-efficiency
- Context engineering
- Prompting techniques – Strategizing prompting techniques, and inventing on the fly when needed
- Hands-on software development experience, preferably in Python or Java, with the ability to build internal tools, develop analysis pipelines and automation scripts, interpret system specifications and technical documentation.
- Harness engineering and tooling
- Evaluating and selecting foundation models for specific use cases
- Establishing guardrails – content filtering, output validation, safety checks
- Building evaluation pipelines – automated test suites and regression testing to catch prompt/model drift
- Version-controlling prompts alongside code – prompt registries, CI/CD for prompt changes
- Monitoring production LLM behaviour – latency, token costs, output quality, failure rates
- Setting up A/B testing frameworks to compare prompt or model variants
Experience in the following areas will be considered an asset:
- Collaborating closely with developers to integrate LLMs into applications
- Agentic frameworks and orchestration tooling
- Evaluating foundation models across multiple providers
- CI/CD pipelines
- Working in agile teams
- Prior experience with fine tuning transformer-like models or local LLMs
- Dataset creation, curation and augmentation
Why join us?
- Work on meaningful AI projects with real-world impact
- Hybrid work model
- Be part of a collaborative, agile team environment
- Opportunity to grow your skills and work with cutting-edge LLM technology
- Culture that values quality, ownership and continuous learning