Senior ML Engineer — Hybrid (Metadata Extraction & AI)

Box; Warszawa; Hybrid; PLN 180,000 - 300,000; Full time

Job summary

Box Poland is seeking a Machine Learning Engineer to design, build, and operate production ML systems that deliver product impact at enterprise scale. You will develop and maintain reliable LM agents, data pipelines, and APIs, collaborating with engineering, product, and data teams.

You will work on an agile stack, use Python extensively, and contribute to monitoring, testing, and operational excellence of AI-powered features for customers.

Qualifications

• 3+ years of experience building, deploying, or operating production software, data, or ML systems.
• Strong Python skills, production-grade, readable, testable code.
• Experience with LLM based agents lifecycle: data/eval-set prep, prompting, tool schemas, RAG, eval, deployment, monitoring.
• Experience with LLM frameworks/libraries (LangChain, LangGraph, PyTorch, Pydantic, Pandas, NumPy) and LLM APIs.

Responsibilities

• Design, build, deploy, and maintain production LLM agents, models, and services.
• Develop data prep pipelines, prompts, tool design, and agentic workflows.
• Write high-quality Python for production systems and maintainable code.
• Collaborate with Product, Software Engineering, Data, and Infra teams to deliver ML capabilities.
• Evaluate agent quality with offline/online metrics and feedback loops.
• Monitor ML systems for quality, latency, cost, and drift; resolve issues.
• Contribute to scalable services/pipelines for real-time and batch ML workloads.
• Create designs, docs, tests, and runbooks; share best practices.

Skills

Python

LLM agents lifecycle

LangChain

LangGraph

PyTorch

Pydantic

Pandas

NumPy

LLM APIs

Cloud deployment

CI/CD

Observability

Testing

Production support

Communication

Ownership

Tools

LangChain

LangGraph

PyTorch

Pydantic

Pandas

NumPy

Job description

Box Poland is seeking a Machine Learning Engineer to design, build, and operate production ML systems that deliver product impact at enterprise scale. You will develop and maintain reliable LM agents, data pipelines, and APIs, collaborating with engineering, product, and data teams.

You will work on an agile stack, use Python extensively, and contribute to monitoring, testing, and operational excellence of AI-powered features for customers.