Senior Data Engineer (Search Platform) (m/f/x)

Das ist der Job

Base pay range Compensation Range: €80K - €110K About Us We’re Cortea, a Berlin startup transforming audits with AI.

Darum lohnt es sich

What we offer High impact & growth: Shape strategy at a scaling AI startup from day one Mission‑driven culture: Ambitious team valuing first‑principles thinking and bold ideas Competitive compensation: €80-€120k salary plus significant equity Personal development: Learning budget for courses and conferences Startup perks: Flexible vacation, team lunches, retreats, central Berlin office Interview process First Call — Intro to Cortea with our Founders Associate Leon Second Call — Technical interview with Rino Third Call — Deep dive into our culture with Philipp On‑site Half‑Day (Berlin) — Meet the team and work on a real problem together We’re an equal‑opportunity team and encourage women and underrepresented groups to apply. #J-18808-Ljbffr Manual, document‑heavy audits waste expert time; we automate the repetitive parts so experts focus on judgment.

Backed by top‑tier VCs with €10m+ funding, live product, paying customers. We value first‑principles thinking, speed, trust, and kindness. We build side by side in our Berlin office. Your Role Own search at Cortea. You’ll design and ship retrieval, ranking, and evaluation systems that power our AI agents.

You’ll also build the data pipelines behind them. You’ll work closely with product, design, and founders to turn messy, real‑world documents into precise answers.

What You’ll Do Build and tune retrieval and ranking: lexical + neural Own evaluation: datasets, metrics, dashboards, and regressions Design data pipelines for ingestion, enrichment and classification Ship production code: Python services, APIs, SQL models, tests Improve relevance through experimentation and systematic analysis Qualifications 5+ years as a software engineer or applied scientist with hands‑on information retrieval work Data engineering experience IR fundamentals: BM25, TF‑IDF, and neural retrieval Evaluation: comfortable with NDCG, MRR, Precision@K and when to use each Data & software: Python (asyncio, type hints, pandas) and strong SQL (modeling, window functions, CTEs, optimization) Production APIs: design, implementation, and maintenance Bonus Ranking systems: learning‑to‑rank, re‑ranking, relevance tuning Distributed compute / orchestration: Spark, Ray, or Temporal Search engines: Elasticsearch / OpenSearch at scale Warehouses: BigQuery, Snowflake, or similar Post‑training LMs for retrieval/ranking No one checks every box.

If you’ve shipped retrieval systems and like owning evaluations and pipelines, let’s talk.