LLM Application Engineer
Bjak · Remote · Switzerland ·
COMPENSATION
€•• – ••k
Listed on the employer's job board (Ashby)
- Fully remote
- LLM & Agent focus
- Python stack
- End-to-end ownership
- Production AI systems
You will work at the intersection of large language models, software engineering, and product design. Your main task is to turn probabilistic model outputs into predictable, safe actions by building robust orchestration pipelines and evaluation systems.
The team focuses on high reliability for long-running workflows and persistent context. You will collaborate with product and engineering groups to translate ambiguous problems into working AI solutions that reduce hallucinations and improve task completion.
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 model, orchestration, and backend layers
- Optimize AI systems for quality, latency, and cost efficiency
- Establish production practices for observability and tracing
What you'll need
- Strong software engineering fundamentals
- Experience building AI-powered applications
- Hands-on work 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 ambiguous environments
- Bias toward shipping and continuous improvement
Stack
- Python
- LLM APIs
- OpenAI-compatible APIs
- Open-weight models
- Agent frameworks
- Vector databases
- Retrieval systems
- Backend services
- Distributed systems
- PyTorch
- JAX