Data Scientist, AI Volta software
Plateforme IA pour automatiser les workflows B2B.
Permanent
Paris, Milan
A few days home
Salary: Not specified
> 3 years
5 years of study
Skills we're looking for
Vertex AI
Elasticsearch
Pandas
Gemini
OpenAI
+4
You'll be part of
Paris, Milano
40 employees
Software
Artificial Intelligence / Machine Learning
SaaS / Cloud Services
Average age: 32
Founded in 2024
Revenue: 2M€
Volta est la plateforme d’exécution IA pour la distribution B2B. Elle se connecte aux systèmes existants et déploie des agents IA pour traiter les demandes entrantes — quel que soit le canal (email, PDF, EDI, WhatsApp…) — et exécuter les workflows opérationnels, commandes, devis, service client, de bout en bout, sous le contrôle des équipes.
Fondée en 2024 entre Paris et Milan par Paul Guillemin et Mario Parteli, Volta réunit une expertise en IA, en logiciel et en distribution.
Volts a levé 11M€ auprès d’un réseau de plus de 50 investisseurs — entrepreneurs du numérique, dirigeants expérimentés du secteur et familles industrielles. Parmi eux, Pascal Houillon, ancien PDG de Cegid et de Sage, et Paolo Grue, ancien PDG de P&G, aux côtés de fonds ayant soutenu Lovable, Qonto, Datadog et Delivery Hero.
Volta aide distributeurs, grossistes, fabricants et marques à transformer des processus complexes et manuels en workflows exécutés par l’IA et supervisés par leurs équipes.
You'll be working on
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
We're looking for
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.
Benefits
How we hire
Screen with the Chief of Staff (30 min): scope, seniority, motivation
Technical deep dive with the CTO and the Head of AI (60 min): we share a small anonymised set of purchase orders, a catalogue extract and the AI output. You find the error patterns, propose how to measure them and which fix comes first. No take-home
Culture and founder conversation (45 min)
Reference checks
Key figures
In short
Founding year
2024
Employees
40
Average age
32
Annual revenue
2M€
Gender
