6 days ago
Remote, Slovakia or Bratislava, SlovakiaMid Level
Responsibilities
- Design and build agent systems using tool calling, orchestration, memory, context management, and customer-data integrations.
- Develop guardrails and human-in-the-loop workflows that allow agents to take actions safely on customer accounts.
- Maintain and improve ML pipelines, model training workflows, and inference services.
- Build and improve classical ML models for personalization and targeting.
- Investigate production issues by analyzing logs, model inputs, and outputs, then identify root causes and ship improvements.
- Collaborate with data scientists, ML/AI engineers, product managers, and other teams to deliver customer-focused ML/AI solutions.
- Write clean, tested, and documented Python code while following collaborative engineering practices.
Requirements
- M.Sc. in Computer Science, Mathematics, Statistics, Data Science, or a related field.
- At least 3 years of professional experience as an ML Engineer, AI Engineer, Data Scientist, or in a similar applied ML role, including meaningful production ML or AI development.
- Fluency in Python and strong software engineering fundamentals, including Git and modern collaborative development workflows.
- Strong understanding of ML algorithms, evaluation, and model behavior, with judgment about when classical models are preferable to LLMs.
- Experience with Docker, Kubernetes, AWS or GCP, CI/CD, and observability tooling such as logging, metrics, and monitoring.
- Hands-on experience with LLM APIs such as OpenAI or Anthropic, including prompt and context engineering, structured outputs, and tool or function calling.
- Hands-on experience with coding agents such as Claude Code.
- Strong analytical, debugging, communication, and cross-functional collaboration skills.
- Nice-to-have experience with agentic AI frameworks such as Claude Agents SDK or Pydantic AI, MCP, LLM observability and evaluation tools, LLM inference optimization, Airflow or similar ML pipeline tooling, and A/B testing infrastructure.
Tech Stack
Categories
About Piano
Piano builds a SaaS digital experience platform that combines analytics, subscription/paywall management, identity, and journey orchestration for publishers and consumer brands. Customers use Piano Analytics and subscription tools to segment audiences, personalize offers, and manage paid relationships across web and apps. Privately held and headquartered in Amsterdam, it serves global enterprises including the BBC, The Telegraph, Nikkei, and The Wall Street Journal.