xelys jobs xelys jobs

LLM Application Engineer

Bjak

midpermanentfullstackbackend Germany 99 days ago via Arbeitnow

See how well this job matches your profile

Sign up to get an AI match score and generate a tailored application in seconds.

Get your match score

Tags

LLM EngineeringAgentic WorkflowsPrompt EngineeringTool CallingEvaluation FrameworksObservabilityTracingExperimentationVector DatabasesRAG

About the role

Role overview

As an LLM Application Engineer, you will build the intelligence layer powering A1’s AI experiences. You’ll work at the intersection of LLMs, software engineering, and product, turning AI capabilities into reliable user experiences.

Responsibilities

  • Own problems end-to-end, from understanding user needs to delivering production AI features.
  • Design agent workflows (planning, reasoning, memory, tool use) and multi-step execution.
  • Build reliable orchestration pipelines that convert probabilistic model outputs into predictable, observable, safe actions.
  • Integrate LLMs with APIs, databases, search, internal services, and external tools.
  • Develop and improve prompting, context engineering, structured outputs, and tool-calling.
  • Create evaluation frameworks and datasets to measure AI quality, reliability, and regressions.
  • Debug across the stack: model behavior and prompts, orchestration, backend services, and product UX.
  • Optimize for quality, latency, and cost.
  • Partner with product and engineering teams to turn ambiguous problems into working solutions.
  • Establish production practices for observability, tracing, experimentation, and continuous improvement.

Requirements

  • Strong software engineering fundamentals with experience building AI-powered applications.
  • Hands-on experience with LLMs/generative AI/agent-based systems.
  • Experience designing prompts, workflows, evaluations, or AI behavior.
  • Ability to write clean, production-quality code.
  • Comfort working across layers (model → system → product).
  • Strong problem-solving in ambiguous, fast-moving environments.

Nice-to-haves / preferred signals

  • Bias toward shipping, iteration, and continuous improvement.
  • Proven ability to deliver measurable user impact and maintain reliability in non-deterministic systems.

About Bjak

Bjak (A1) is building AI-native experiences for everyday tasks like conversations, errands, organization, and workflows. The product focuses on reliable, long-running agent workflows with persistent context and real-world task completion using LLM-powered systems.

Scraped 8/15/2026