AI Automation and Data Platform Lead

ASC GLOBAL POLSKA sp. z o.o.; Województwo mazowieckie; Hybrid; PLN 210,000 - 360,000; Full time

Benefits offered by this job

Hybrid work

Competitive salary

Contract Flexibility - B2B or emp

Job summary

ASC Global Polska sp. z o.o. is building an AI-driven, global sourcing platform.

You’ll be the first/lead engineer, shaping architecture, data model, and crawling pipelines. This hands-on role requires writing code, deploying the system, and running workshops to drive adoption across Sales, Purchasing, Operations and Finance. You’ll own end-to-end platform development, connect to Zoho CRM RFQ workflow, and lead efforts to scale from initial 10 sources to hundreds, delivering measurable time

Qualifications

• 5+ years hands-on software or data-engineering experience.
• Production ownership of a web-crawling or data-acquisition system you built or operated.
• Advanced Python and strong SQL.
• Experience with Scrapy and browser automation for JS-rendered sites.
• Solid HTTP, rate limiting, retries, queues and failure recovery.
• Normalization of messy, conflicting data into a canonical model.
• Entity resolution with measured accuracy; deduplication work.
• PostgreSQL or similar, plus Docker and a major cloud platform (AWS, GCP or Azure).
• Production experience with LLM APIs using deterministic checks.
• Implemented an AI/automation solution across multiple departments.
• Translate business needs into clear technical requirements; run workshops.
• Fluent English.

Responsibilities

• Architect, build and operate crawling, data-ingestion, normalization and matching platform.
• Handle static/JS-rendered sites, PDFs, pagination and multilingual content.
• Build reliable crawling infra: rate limiting, retries, queues, backoffs, failure recovery.
• Design canonical product/supplier/offer data model with provenance history.
• Develop entity-resolution and deduplication with accuracy reporting.
• Set up source-health monitoring and alerts for bad data sources.
• Utilize LLMs where valuable with evaluation, thresholds and human review.
• Integrate platform with Zoho CRM RFQ workflow and QuickBooks.
• Deliver milestones: architecture, 10 sources, searchable data, accuracy monitoring, Zoho RFQ integration.
• Plan scaling to hundreds of sources and drive AI adoption across departments.
• Run workshops and training to ensure adoption; act as technical owner.

Skills

Hands-on software or data-engineering

Production ownership

Python

SQL

Scrapy

Playwright

Selenium

HTTP & retries

Data normalization

Entity resolution

PostgreSQL

Docker

Cloud platforms (AWS/GCP/Azure)

LLM APIs in production

Cross-department AI initiatives

Technical requirement gathering

Workshops & training

Fluent English

Education

Tools

Scrapy

Playwright

Selenium

Zoho CRM RFQ integration

QuickBooks integration

Job description

Nasze wymagania:

• 5+ years of hands‑on software or data‑engineering experience
• Proven production ownership of a web‑crawling or large‑scale data‑acquisition system you personally built or operated, not personal projects or coursework
• Advanced Python and strong SQL
• Experience with a production crawling framework (e.g. Scrapy) and browser automation (Playwright or Selenium) for JavaScript‑rendered sites
• Solid grounding in HTTP, rate limiting, retries, queues and failure recovery
• Experience building normalized pipelines from messy, conflicting data
• Hands‑on entity resolution, fuzzy matching or deduplication work, backed by real accuracy numbers
• Strong PostgreSQL (or similar), plus Docker and at least one major cloud platform (AWS, GCP or Azure)
• Production experience with LLM APIs (structured outputs, evaluation, cost control), using them alongside deterministic checks rather than instead of them
• Have personally implemented an AI or automation solution inside a real company, not just used the tools, ideally across more than one department
• Able to translate business needs into clear technical requirements and explain technical work to non‑technical colleagues
• Comfortable running workshops and training to help people adopt new tools
• Fluent English

O projekcie:

ASC Global is a global independent distributor and sourcing company serving the electronic components, computer and data‑center, industrial MRO and aviation MRO markets. We source semiconductors, passive components, interconnect products, memory, computer hardware, data‑center infrastructure and industrial/aviation parts from suppliers worldwide.

We’re building an AI‑driven global sourcing and product‑intelligence platform. It will continuously monitor hundreds of distributor sites, broker inventories, marketplaces and manufacturer sources. It will identify products, capture pricing and availability, and match every listing to the real, canonical part, so our buyers and sales team can find the right parts faster and quote with confidence.

What the platform does:

• Crawls and ingests data from static and JavaScript‑rendered sites, PDFs, paginated catalogs and multilingual content
• Normalizes messy, conflicting supplier data into one clean product/supplier/offer data model
• Matches listings to real parts through entity resolution, with measured matching accuracy
• Keeps full source provenance on every record: where it came from, when, and how it changed
• Monitors source health, so broken sites or bad data are caught automatically
• Uses LLMs where they genuinely help (extraction, translation, classification), with evaluation, confidence thresholds and human review, and never lets a model guess a price or quantity it can’t find
• Connects to our Zoho CRM RFQ workflow and, downstream, QuickBooks

Stage of development:

This is an early‑stage, greenfield build. You’ll set the architecture and data model from the start, as the first/lead engineer on the platform. It’s a hands‑on role: you write the code, deploy the system, and run the workshops that get people using it.

Milestones for the first 90 days and beyond:

• A working architecture and data model within 90 days
• At least 10 sources connected with full provenance
• Searchable, normalized product and supplier data
• Measured matching accuracy and source‑health monitoring in place
• An initial Zoho RFQ integration
• Then: scaling toward hundreds of sources, measurable time savings, and broader AI adoption across departments

Duration:

Long‑term, permanent role with ownership of the platform from first build through scaling.

Zakres obowiązków:

• Architect, build and operate the crawling, data‑ingestion, normalization and matching platform, from first design through production
• Handle static and JavaScript‑rendered sites, PDFs, pagination and multilingual content, using the right tool for each (plain HTTP vs. browser automation)
• Build reliable crawling infrastructure: rate limiting, retries, queues, backoff and failure recovery
• Design the canonical product/supplier/offer data model, keeping full source provenance and change history on every record
• Develop entity‑resolution and deduplication logic that matches supplier listings to real, canonical parts, and measure and report its accuracy
• Set up source‑health monitoring and alerts so broken sources or bad data are caught automatically
• Use LLMs where they genuinely add value (extraction, translation, classification), with evaluation, confidence thresholds, cost control and human review, and never let a model guess a price or quantity
• Integrate the platform with Zoho CRM’s RFQ workflow and, downstream, QuickBooks
• Deliver the first‑90‑day milestones: working architecture and data model, at least 10 sources connected, searchable normalized data, measured matching accuracy, monitoring and an initial Zoho RFQ integration
• Create and maintain a documented plan for scaling the platform to hundreds of sources
• Work directly with Sales, Purchasing, Operations, Finance and leadership to find processes AI or automation can improve
• Turn those opportunities into clear requirements and real pilots, and track the impact in hours saved and sourcing turnaround
• Run workshops and training so employees actually adopt the tools that get built
• Act as the go‑to technical owner for the platform, translating between business needs and engineering

Oferujemy:

• The chance to build an AI‑driven global sourcing platform from the ground up, as the first/lead engineer
• Real ownership: you set the architecture, data model and technology choices
• A rare hybrid role combining hands‑on engineering with leading AI adoption across a global business
• Direct access to leadership, buyers, sales and operations, with no layers between you and the people using what you build
• Visible, measurable impact on how a global distributor sources and sells
• Freedom to experiment with AI and automation, and to turn the best ideas into real pilots
• A complex, interesting data domain: millions of parts across electronic components, data‑center, industrial and aviation markets
• Work with a global company and international suppliers and customers
• Hybrid work
• Competitive salary
• Contract Flexibility - B2B or employment contract
• Paid time off, Sports Card Support