Lead the optimization of the inference stack (throughput, latency, cold starts, cost per token) across GPU fleets and customer clusters. Responsibilities include profiling and benchmarking, scheduler and KV-cache tuning, weight loader and JIT/cache improvements, quantization without quality regressions, and scaling distributed inference topologies. Tech stack includes Python, vLLM, SGLang, TensorRT-LLM, PyTorch, CUDA tooling, Kubernetes, virtiofs/shared filesystems, ClickHouse, observability and CI tooling.

Own the end-to-end routing model: features, objective, training, calibration, evaluation, and rollout (shadow, A/B, full). Work with production fleet data, benchmark harnesses, and platform engineers to instrument per-request signals (including decode speed) and ensure production-parity with rigorous evals and error bars. Tech stack highlights: Python, PyTorch, SQL at scale (ClickHouse), OpenAI/Anthropic-compatible LLM APIs, and GitLab CI.

Remote-first Senior Data Scientist role (requires 7+ years experience) at DuckDuckGo. Responsibilities include statistical modeling, experiment design and analysis, Bayesian campaign measurement, classifier implementation, NLP and LLM work (including fine-tuning), and deploying and iterating ML in production for search, AI features, and revenue optimization. Role requires production-grade Python, advanced SQL and familiarity with columnar DBs (BigQuery, ClickHouse, Redshift, Druid); work involves privacy-constrained data. Position is remote in the listed countries and requires travel roughly twice a year for company events.

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.

Design and implement ML models that scale to millions of requests per second, translate business requirements into technical specifications, evaluate and debug models, and provide technical mentorship. Role combines research, engineering, and deployment work in a fully remote, flexible-hours environment. Requires 5+ years professional applied ML experience and experience with real-time, incremental, and online learning.

Lead and architect large-scale, production ML projects from design through deployment and maintenance. Require 7+ years building and maintaining production ML systems with focus on scalability, performance, reliability, and leadership. Familiarity with Kubernetes, containerization, distributed systems, and experience mentoring other ML engineers. Positions listed for Poland, Romania, Austria, and Croatia; role is fully remote with flexible hours.