Back
Niche LLM plus web-crawling requirements reduce applicants, but mid-level (5+ yrs) increases competition.
Core LLM, Python, and web-crawling skills are transferable across industries, though healthcare compliance adds domain specificity.
Multiple mandatory specialized skills plus explicit 5+ years Python requirement produce high shortlisting strictness.
Login to See Your Match Score
Create a free account or log in to unlock your CV match score across:
Own and enhance a production-ready proof of concept integrating resilient web-crawling engineering with an AWS Bedrock-based large language model (LLM) verification agent in a healthcare data compliance context.
Develop and maintain multi-module Python packages including adapters, caching layers, and CLI tools, focusing on typed, idiomatic code and data modeling with Pydantic.
Design deterministic-first hybrid LLM pipelines combining traditional code logic and LLM judgement, implement web scraping with advanced anti-detection strategies, and automate browser workflows with Playwright or equivalents.
5+ years of expert-level Python programming experience, including idiomatic and typed data modeling using Pydantic.
Proven expertise in web scraping/crawling with tools like httpx/requests, BeautifulSoup, and techniques for rate limiting and evasion of scraping defenses.
Experience with browser automation frameworks like Playwright, Selenium, or Puppeteer involving scripted logins and client-side rendered content handling.
Proficiency with AWS core services including Bedrock, boto3, IAM roles/STS, and document processing with tools like PyMuPDF. Work Experience Required: Explicitly 5+ years Python experience.
Strong background in building robust web data extraction systems combining scripting, crawling, and browser automation optimized for complex, hostile targets.
Experience architecting hybrid AI/agentic solutions leveraging AWS Bedrock and LLMs (Claude) within regulated or compliance-sensitive healthcare domains.
Comfortable working with multi-component software projects integrating cloud-native AWS services and advanced document and data processing pipelines.