Lead technical direction for LLM inference optimization (Kimchi), improving throughput, lowering latency, and maximizing KV cache efficiency across GPU SKUs and distributed topologies. Requires 5+ years building ML systems/inference or training infrastructure, strong Python, hands-on experience with vLLM/SGLang/TensorRT-LLM, quantization fluency, distributed systems knowledge, and a measurement-first approach. Remote-first role available in multiple European countries.

Work on end-to-end production search and ML/AI services: design architectures, build scalable web services and data pipelines, deploy and monitor solutions, and mentor junior engineers. Requires 7+ years' experience, expert-level Python, search and clickstream analytics; experience with Elasticsearch, vector search, recommendation engines, Redis, and cloud (e.g., AWS) is a plus.

Sardine is hiring a Senior Data Scientist to design, prototype, and productionize machine learning and graph analytics solutions for fraud and risk use cases. The role involves client-facing problem solving, metrics definition, dashboard automation, collaboration with engineering to scale models, and requires 7+ years of relevant data science or quantitative experience with strong Python/R and SQL skills.

Prezi is hiring a Senior Data Analyst to join the Data Science & Analytics team (remote across listed European countries). The role involves end-to-end analyses (requirements, data processing, presentation), building dashboards and data products, defining metrics, quantifying impact, fostering self-service analytics, and collaborating with data engineering. Required: 5+ years in data/business analytics, proficiency in SQL and Python (or other scripting), experience with statistical analyses (funnel analysis, clustering, forecasting, recommender systems), dashboard building, strong English communication, and interest/experience in AI tools. Bonus experience: AWS, ETL pipelines, SaaS analytics, personalization/recommendation work.

Remote Senior ML Ops Engineer role focused on maintaining and extending data/ML workflows and platforms that handle high-velocity, large-scale data. Requires minimum 3 years in a data role (data stores, feature engineering, pipelines) and at least 2 years of professional software development experience; key technologies include Python, Kafka, SQL/NoSQL (ClickHouse), cloud (AWS/Azure), Kubernetes and CI/CD.