ENTRADA AI SPÓŁKA Z OGRANICZONĄ ODPOWIEDZIALNOŚCIĄ

AI Architect (Generative AI & Databricks)

~200 - 250 PLN/ godz./ godz.B2BB2B (netto)

SeniorZdalnie·KrakówFull-time·B2B

#464590·Dodano 13 dni temu·5

Źródło: justjoin.it

Aplikuj teraz

Tech Stack / Keywords

AIDatabricks LLMsUnity CatalogStreamlitdash

Podsumowanie oferty

Lead the design and implementation of an enterprise GenAI platform for a client, automating the processing and verification of commercial pricing requests. Architect ingestion and extraction workflows using Databricks, LLMs, and PySpark, including a human review application built with Databricks Apps.

Wymagania

Bachelor’s or Master’s degree in Computer Science, Artificial Intelligence, Data Engineering, or a related field.
7+ years of experience in data engineering, data architecture, or applied machine learning systems.
4+ years of hands-on experience designing and deploying solutions on the Databricks Lakehouse Platform, including Unity Catalog, Delta Lake, Databricks Model Serving, and Databricks SQL.
Experience building structured extraction pipelines using function calling, Pydantic validation, and custom guardrail and citation-verification systems as an Applied GenAI/LLMOps Engineer or Architect.
Experience parsing semi-structured and unstructured business documents using Python and PySpark libraries, including PyMuPDF, pdfplumber, OpenPyXL, and BeautifulSoup4.
Experience developing interactive data applications using Streamlit or Dash, including deploying containerized apps natively inside Databricks Apps.
Understanding of enterprise identity and API integrations, including Microsoft Graph API, OAuth 2.0 client credential flows, Microsoft Entra ID (Azure AD), and Databricks Secret Scopes.
Background in data modeling, governance, and auditability inside Unity Catalog, including Volumes, Delta Tables, ACLs, and row- and column-level security.
Experience or working familiarity with downstream enterprise ERP integration patterns.
Strong problem-solving and analytical skills; ability to design resilient, production-ready systems that prevent hallucinated data from reaching financial systems of record.
Excellent communication, consulting, and client-facing skills, including the ability to explain GenAI concepts to technical teams and executive business stakeholders.

Obowiązki

Design and oversee end-to-end GenAI Lakehouse architecture on Databricks, turning unstructured email threads and attachments into verified, ERP-ready tabular data.
Architect secure, incremental ingestion pipelines via Microsoft Graph API and PySpark parsing engines, processing PDFs, Excel workbooks, and HTML into Unity Catalog Volumes and Bronze Delta tables.
Lead deterministic extraction workflows on Databricks Model Serving (Claude/GPT), using strict Pydantic schemas to extract commercial attributes.
Implement a three-layer anti-hallucination verification engine using schema constraints, source citations, and PySpark string assertions.
Architect and deploy an interactive Human-in-the-Loop (HITL) review application on Databricks Apps (Streamlit/Dash) with side-by-side reconciliation, manual overrides, and secure SSO/OBO authentication.
Model Gold-layer pricing staging tables and design automated batch feeds for downstream ERP consumption via Databricks SQL Warehouses and REST APIs.
Establish best practices for Unity Catalog governance, data lineage, error-quarantine routing, and system security across client engineering teams.
Create and maintain architectural documentation, data models, and interface specifications; mentor client teams.

Benefity

An Apple MacBook Air M4 15-inch provided to engineers.
Referral bonus for bringing other engineers to the team.
Coverage for Databricks technical certifications.
Support in pursuing advanced Databricks expertise, including the Champion program, tailored to the career track.
Opportunities to present at global industry conferences and contribute to technical thought leadership.
Direct collaboration with Databricks MVPs and core product teams.

Premie

Dofinansowanie szkoleń

Inne informacje

Remote work is available from anywhere in Poland, Romania, or Greece.
Recruitment process: a 20-minute introductory call, a 60-minute technical interview, an optional client interview in specific cases, then a decision and offer.

ENTRADA AI SPÓŁKA Z OGRANICZONĄ ODPOWIEDZIALNOŚCIĄ

4 aktywne oferty

Zobacz wszystkie oferty

Aplikuj teraz