LLM Application Engineer
Bjak · Remote · Germany ·
COMPENSATION
€•• – ••k
Listed on the employer's job board (Ashby)
- Fully remote
- LLM & Agent focus
- Python stack
- Build AI workflows
- Production quality
You will work at the intersection of large language models, software engineering, and product design. Your main goal is to design agentic workflows, improve model behavior, and ensure high reliability for long-running tasks and persistent context.
The team focuses on reducing hallucinations and organizing users' lives through intelligent conversations and workflow automation. You will own problems end-to-end, from understanding user needs to building evaluation systems and optimizing production performance.
What you'll do
- Build and ship LLM-powered applications and AI agent workflows
- Design systems for reasoning, planning, memory, and tool use
- Create orchestration pipelines for predictable and safe actions
- Integrate LLMs with APIs, databases, search, and external tools
- Develop prompting and context engineering techniques to improve behavior
- Build evaluation frameworks to measure AI quality and reliability
- Debug AI systems across the entire stack from model to UX
- Optimize AI systems for quality, latency, and cost efficiency
- Collaborate with product teams to solve ambiguous problems
- Establish production practices for observability and tracing
What you'll need
- Strong software engineering fundamentals
- Experience building AI-powered applications
- Hands-on experience with LLMs or agent-based systems
- Experience designing prompts, workflows, or evaluations
- Ability to write clean, production-quality code
- Comfortable working across model, system, and product layers
- Strong problem-solving skills in fast-moving environments
- Bias toward shipping, iteration, and continuous improvement
Stack
- Python
- LLM APIs
- OpenAI-compatible APIs
- Agent frameworks
- Vector databases
- Backend services
- Distributed systems
- PyTorch
- JAX