LLM Application Engineer
Bjak · Remote · Poland ·
COMPENSATION
€•• – ••k
Listed on the employer's job board (Ashby)
- Fully remote
- LLM Application Engineer
- Python + PyTorch
- Agent workflows
- Senior level
You will work at the intersection of large language models, software engineering, and product design. Your main goal is to design agent workflows, improve model behavior, and transform AI capabilities into reliable experiences for users who do not use complex prompting.
The team focuses on high reliability for long-running workflows, persistent context, and real-world task completion. You will own problems end-to-end, from understanding user needs to building evaluation systems and continuously improving AI behavior in production.
What you'll do
- Build and ship LLM-powered applications and AI agent workflows
- Design systems for reasoning, planning, memory, and multi-step execution
- Create orchestration pipelines that ensure safe and predictable actions
- Integrate LLMs with APIs, databases, search, and external tools
- Develop prompting and context engineering techniques to improve model behavior
- Build evaluation frameworks to measure AI quality and reliability
- Debug AI systems across the stack from prompts to backend services
- Optimize AI systems for quality, latency, and cost efficiency
What you'll need
- Strong software engineering fundamentals with AI application experience
- Hands-on experience with LLMs, generative AI, or agent-based systems
- Experience designing prompts, workflows, evaluations, or AI behavior
- Ability to write clean, production-quality code
- Comfortable working across model, system, and product abstraction layers
- Strong problem-solving skills in ambiguous and fast-moving environments
- Bias toward shipping, iteration, and continuous improvement
Stack
- Python
- LLM APIs
- OpenAI-compatible APIs
- Agent frameworks
- Vector databases
- PyTorch
- JAX