AI Automation Lead

ASC Global

. Build and operate the crawling, data-ingestion, normalization and matching platform .

Posted 9/18/2026full-timeRemote • United StatesSeniorWebsite

Core Competencies

Role fit

Core Competencies

Use this summary to align your resume positioning with the role.

Demonstrates expertise in building and operating data ingestion and normalization platforms, with a strong focus on web crawling, entity resolution, and integration with CRM and ERP systems. Proficient in leveraging LLMs for data extraction and classification while ensuring data accuracy and provenance.

Highest-signal resume keywords

Advanced PythonStrong SQLWeb Crawling Framework (Scrapy)Entity Resolution / Fuzzy MatchingLLM API Integration

ATS Keywords

Tailor your resume

Applicant Tracking System Keywords

Tip: use these terms in your resume and cover letter to boost ATS matches.

Hard Skills

Data EngineeringData NormalizationEntity ResolutionFuzzy MatchingDeduplicationPostgreSQLDockerCloud PlatformJavaScript RenderingProduction Ownership

Soft Skills

TrainingCross-Department CollaborationBusiness Needs Translation

Tools & Technologies

ScrapyPlaywrightSeleniumZoho CRMQuickBooksTemporalDagsterPrefectAirflowOpenSearch

Industry Keywords

Data Acquisition SystemsCrawlingData PipelinesSource ProvenanceAutomation SolutionsTechnical Catalogs

Tech Stack

Tools & technologies

AirflowCloudDockerElasticSearchERPJavaScriptPostgresPythonSeleniumSQL

About the role

Key responsibilities & impact

Build and operate the crawling, data-ingestion, normalization and matching platform
Handle static and JavaScript-rendered sites, PDFs, pagination and multilingual content
Maintain full source provenance on every record
Design the canonical product, supplier and offer data model
Build entity-resolution logic that matches listings to real parts
Use LLMs for extraction, translation and classification with evaluation, confidence thresholds and human review
Connect the platform to Zoho CRM's RFQ workflow and, downstream, QuickBooks
Work with Sales, Purchasing, Operations and Finance to identify AI and automation opportunities
Turn opportunities into practical pilots, train employees and track impact
Deliver a working architecture and data model within the first 90 days
Connect at least 10 sources with full provenance
Provide searchable, normalized product and supplier data
Measure matching accuracy and implement source-health monitoring
Deliver an initial Zoho RFQ integration
Create a documented plan for scaling to hundreds of sources

Requirements

What you’ll need

Five or more years of hands-on software/data-engineering experience with real production ownership of web-crawling or large-scale data-acquisition systems — 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, plus entity resolution / fuzzy matching / deduplication work backed by real accuracy numbers
Strong PostgreSQL (or similar), plus Docker and at least one major cloud platform
Comfortable using LLM APIs in production — structured outputs, evaluation, cost control — without treating them as a replacement for deterministic checks
Personally implemented an AI or automation solution inside a real company, ideally across more than one department
Comfortable running training and translating business needs into requirements for other engineers
Nice to have: Temporal, Dagster, Prefect or Airflow
Nice to have: OpenSearch or Elasticsearch
Nice to have: RapidFuzz, Splink or embeddings-based matching
Nice to have: Zoho, Salesforce, HubSpot, QuickBooks or other ERP integrations
Nice to have: Electronic components or other complex technical catalogs
Nice to have: Prior experience as the first or lead engineer on a new platform