Salary: 65.000 - 108.000 € per year Requirements: University degree in Computer Science, Engineering, or a related field. Several years of experience in applied machine learning and model engineering. Proficient in PyTorch and Transformers frameworks. Expertise in model compression, alignment, and fine-tuning of small GenAI and ML models. Skilled in building evaluation suites and performing statistical analysis of model behaviour. Practical knowledge of edge device constraints such as RAM, bandwidth, cache, and cold start. Professional English proficiency, German is a plus. Responsibilities: Select and adapt base models for voice assistant and intelligence tasks. Produce clean, reproducible training, finetuning and evaluation pipelines to refine models for the problem at hand. Implement required compression strategies such as quantization, pruning and distillation to enable cost-efficient inference. Collaborate with performance engineers on hardware-aware model variants and performance. Co-own latency and memory KPIs and provide models that meet budget requirements on the target hardware. Document design choices, trade-offs and model cards for audits and compliance. Technologies: Hardware Machine Learning PyTorch Security AI More: We are an international team of experts shaping the future of intelligent mobility by developing and refining edge GenAI models for the BMW Intelligent Personal Assistant. Together, we deliver customer impact through innovative model engineering and robust data pipelines. We offer challenging projects that shape the mobility of tomorrow, a wide range of personal and professional development opportunities, attractive remuneration, high job security, and flexible working hours, including 6 weeks annual leave. Our company values equal treatment and opportunities for all applicants. last updated 18 week of 2026