Senior Software Engineer (Web Scraping Gen AI Developer)

About the role: We are looking for a senior AI engineer 56 years of experience) to help us automate and improve our web scraping operations using AI. We mainly aim to reduce manual effort and improve efficiency across our scraping team, by building intelligent systems that can: Extract data more autonomously. Detect issues before they affect production. Automatically adapt to website changes. Improve code/data QA. Reduce development and maintenance time.

Responsibilities

Design, build, and deploy AI-powered automation and LLM-based workflows (chatbots, copilots) for real-world scraping issues to detect scraping failures and anomalies and identify data issues; Fine-tune, evaluate and optimize AI models for performance and scalability; Implement smart alerting systems to reduce noise and focus on real issues; Build AI-assisted tools to debug scraping issues and recommend fixes or generate updated logic to reduce manual maintenance effort for scraping pipelines; Collaborate with scraping team to translate scraping/business requirements into AI-driven solutions; Continuously monitor and improve performance, reliability, and cost efficiency of AI solutions in production environments; Maintain documentation, testing procedures, and deployment workflows

Requirements

5-6+ years of experience in AI/ML engineering or similar roles; Strong Python skills; Strong problem-solving skills to address complex challenges and performance bottlenecks; Advanced knowledge in Machine Learning models and Large Language Models (LLM), using Langchain or a similar tool; Experience in implementing LLMs using vector databases and Retrieval Augmented Generation (RAG), as well as tuning models using GPTs, Llama, or any other LLM; Experience building production-ready systems, not just prototypes and providing support to them; Hands-on experience with containerization (Docker, ideally Kubernetes) and CI/CD workflows; Experience with cloud environments (GCP, Azure or AWS); Excellent technical communication skills to collaborate effectively across teams and explain technical concepts to non-technical stakeholders

Nice to have

Familiarity with web scraping tools (Scrapy, Playwright, Selenium) and data pipelines and distributed systems is a strong plus; Understanding of security best practices for extracting data; Experience in developing and using APIs can be useful for integrating models into existing applications

Benefits

Flexible working environment; Volunteer time off; LinkedIn Learning; Employee-Assistance-Program (EAP)