Design and build ETL/ELT pipelines, own data quality end-to-end, and integrate LLM-powered extraction pipelines. 5+ years of experience in building production data pipelines at scale. Strong SQL and Python skills.
Key Highlights
Key Responsibilities
Technical Skills Required
Benefits & Perks
Job Description
Remote (Europe)
Contract
We're looking for a Senior Data Engineer to join our team.
Most data engineering jobs still treat unstructured data as someone else's problem. Legal documents, contracts, filings, and transcripts get handed off to an ML team that returns a table, which the data engineer then pipelines downstream like any other source — except the source is probabilistic, drifts silently, and quietly breaks the canonical layer when nobody's watching.
At Bonsai Labs, the data engineer owns the path from raw source to a clean, governed silver layer — including the LLM extraction in the middle. You design the prompts, build the evals, monitor for drift, and own the data quality of the canonical model. We're looking for a Senior Data Engineer who ships pipelines end-to-end and treats LLM-augmented ingestion as just another (rigorous) part of the stack.
What you'll do
- Design and build ETL/ELT pipelines on whatever platform the engagement runs on — Snowflake, Databricks, BigQuery, Fabric, or a custom lakehouse — on top of foundations set up by the Data Platform Lead
- Build canonical and normalized silver/gold layers across complex sources, including messy unstructured ones (legal documents, contracts, filings, transcripts)
- Design and ship LLM-powered extraction pipelines: write the prompts, build evals for extraction accuracy, monitor for drift, define recovery patterns when extractions fail
- Model the silver layer so it stays reliable even when upstream sources are probabilistic
- Integrate vector stores, embeddings, and retrieval indices where they belong in the data flow
- Own data quality end-to-end — monitoring, alerting, and remediation across the pipeline
- Work directly with client teams to translate ambiguous business data into structured, governed assets
Interested in remote work opportunities in Data Science? Discover Data Science Remote Jobs featuring exclusive positions from top companies that offer flexible work arrangements.
What we're looking for
- 5+ years building production data pipelines at scale, with strong SQL and Python
- You're platform-adaptable. You've shipped on at least two of Snowflake, Databricks, BigQuery, or equivalent in production, and you can ramp quickly on a new one. Familiar with dbt and a modern orchestration stack (Airflow, Dagster, or equivalent)
- You've shipped LLM-powered extraction pipelines on messy real-world sources, with evals and monitoring — not just demos
- Familiarity with cloud platforms (Azure, AWS) and the surrounding ecosystem (storage, IAM, secrets, networking)
- You think probabilistically about data quality. You don't trust an LLM extraction that hasn't been measured
- Solid software engineering fundamentals — testable code, clear interfaces, infrastructure as code
- Clear communicator, comfortable in client-facing settings translating fuzzy business requirements into concrete pipelines
Browse our curated collection of remote jobs across all categories and industries, featuring positions from top companies worldwide.
About Bonsai Labs
Bonsai Labs is an AI implementation company. We embed with the world's most ambitious B2B software companies and private equity portfolios to deliver AI that works in production, not in slides. We hire senior practitioners who've shipped AI systems at scale. No junior consultants, no filler. Every person on the team ships.
We work at the frontier of AI deployment. Small team, hard problems, real impact.
Our culture is anchored in four principles:
Ownership over output. We don't hand off decks. We embed with clients and own the outcome end-to-end, from strategy through production deployment.
Engineering excellence. We hire senior practitioners who've built AI systems at scale. No junior consultants, no filler. Every person on the team ships.
Radical transparency. We share context early and often, with each other and with clients. No politics, no information hoarding, no surprises.
AI-native to the core. We live and breathe AI. Every person on this team is obsessed with staying at the absolute frontier of new models, new techniques, and new tools. If it shipped this week, we've already tried it.
Bonsai Labs is a fully remote company with team members across Europe. We are bootstrapped, profitable, and growing.
Equal opportunity. We are an equal opportunity employer. We do not discriminate on the basis of age, disability, gender reassignment, marriage or civil partnership, pregnancy or maternity, race, religion or belief, sex, or sexual orientation, or any other characteristic protected under the UK Equality Act 2010 or applicable EU and national employment law. To achieve our mission, we believe we need to encompass and value the many different perspectives, voices, and experiences that form the full spectrum of humanity.
Ready to do the best work of your career?
Join a team that ships AI into production for the world's most ambitious companies.
Similar Jobs
Explore other opportunities that match your interests
olive tree consulting group
dune talent
Business Analyst (Technology and System Implementation)