Data Scientist, AI

Volta software; Paris; Ibrido; EUR 70.000 - 110.000; Tempo pieno

Descrizione del lavoro

Volta Software seeks an Applied Data Scientist who measures and improves accuracy across orders. You will define per-field metrics, build automated evaluation harnesses and enable scalable, configurable prompts for extraction and matching using LLMs.

You’ll work with Python, SQL and Elasticsearch to handle messy documents, PDFs, and multi-language data, collaborating with enterprise customers to drive measurable improvements.

Competenze

• 3+ years shipping ML or NLP to production.
• Strong Python, Pandas or Polars and testing habits.
• Hands-on with LLM APIs (Gemini, OpenAI, Anthropic or similar).
• Experience with Elasticsearch or similar search and retrieval.
• Experience with evaluation metrics (precision/recall, per-field accuracy).
• Fluent English; French or Italian for documents.

Mansioni

• Define how accuracy is measured per field and track per customer/release.
• Build evaluation harnesses and CI-integrated datasets.
• Improve matching with catalogues and synced master data.
• Turn customer fixes into reusable prompts/configuration templates.
• Perform rigorous error analysis to identify root causes and fixes.
• Turn data issues into structured evaluation outputs.

Conoscenze

Python

Pandas

Polars

Testing habits

LLM APIs

Elasticsearch

SQL

Error analysis

English fluency

French or Italian

Formazione

MSc in CS/Stats/Applied Math

Strumenti

OpenSearch

Langfuse

OCR tooling

GCP

Descrizione del lavoro

You’ll own how accurate Volta’s AI is, and you’ll make it measurably better, customer by customer. You’ll build the evaluation harnesses, run the error analysis and improve extraction and matching on real purchase orders from enterprise customers. You report to the Head of AI: this role is about measurement, retrieval and LLM-based extraction, not about training models.

• Own the accuracy number: we are working towards 90% accuracy across customers. Define how it’s measured per field (customer, ship-to, product, quantity, unit of measure, price), track it per customer and per release, and make it go up

• Build evaluation that runs itself: per-customer evaluation harnesses and golden datasets built from real, anonymised orders, wired into CI so a regression is caught before release, not by the customer

• Make matching better: product and customer matching against catalogues of thousands of SKUs and messy master data, with Elasticsearch-based retrieval, synonyms, reranking and confidence scores

• Improve extraction with LLMs: prompts, schemas and pre-processing steps that turn an email body table, a multi-page PDF or a 100-line spreadsheet into clean order lines

• Do error analysis like an engineer: turn a pile of customer issues into categories, root causes and the one fix that closes ten tickets, then verify in production after the release

• Turn customer fixes into configuration: per-customer behaviour lives in prompts and configuration, not in code branches, and recurring patterns become reusable templates by industry and document type

Applied data scientist who measures things: 3+ years shipping ML or NLP to production, judged on a metric that mattered to users LLM applications in production: extraction, classification or retrieval built on LLM APIs with structured outputs and real evaluation, not only demos or notebooks

Search and matching: entity resolution, record linkage or product search, ideally with Elasticsearch, OpenSearch or hybrid lexical plus vector retrieval

Evaluation discipline: test sets, metrics, label noise and regression tracking over time

Real-world documents: messy PDFs, spreadsheet exports, emails in several languages

Writes production code: Python that other people can review, test and run in CI

Must have: strong Python, pandas or polars and testing habits; hands-on with LLM APIs (Gemini, OpenAI, Anthropic or similar); evaluation datasets and metrics (precision and recall, per-field accuracy, confidence calibration); search and retrieval (Elasticsearch or similar, fuzzy matching, BM25, embeddings, reranking); solid SQL; rigorous error analysis; fluent English; French or Italian (many documents are written in them)

Nice to have: LLM tracing and evaluation tooling (Langfuse or similar); document parsing and OCR; B2B commerce data (catalogues, units of measure, price lists, ERP master data); GCP (Cloud Run, Vertex AI)

Degree: MSc in Computer Science, Statistics, Applied Math, Computational Linguistics or a related quantitative field, or equivalent practical experience

Location: Milan or Paris, hybrid

At Volta, we believe diversity makes our teams stronger. We welcome all applications, regardless of gender, background, or experience.