Attractive salary; not specified; benefits include...
Hybrid
Llm deployment and productionization
Rag system architecture design
Multi-gpu workload optimization
The role focuses on squeezing maximum potential out of hardware to deliver high-quality responses with the lowest possible latency
Job Summary
The role focuses on squeezing maximum potential out of hardware to deliver high-quality responses with the lowest possible latency.
Candidates will design workflows enabling AI to accurately query private information through Retrieval-Augmented Generation systems.
Employees receive benefits including attractive salary, hybrid working models, free canteen access, and extensive upskilling opportunities.
Matching Summary
The role focuses on squeezing maximum potential out of hardware to deliver high-quality responses with the lowest possible latency.
Salary
Attractive salary; Not specified; Benefits include vacation days, health insurance, stock options, retirement plan, study grants, free canteen, kindergarten, medical office
Skills & Requirements
Must-have
LLM deployment and productionization
RAG system architecture design
Multi-GPU workload optimization
Python programming proficiency
Vector database implementation
Nice-to-have
Military avionics domain knowledge
Quantization and model weight reduction
Long-context window management
Kubernetes container orchestration
Air-gapped security environment experience
Key Requirements
3+ years in Machine Learning Engineering or NLP
Degree in Computer, Telecomunications, Maths or Software Engineering