Threat Collections Engineer

Anthropic•San Francisco, WA

19d•Hybrid

About The Position

Anthropic’s mission is to create reliable, interpretable, and steerable AI systems. We want AI to be safe and beneficial for our users and for society as a whole. Our team is a quickly growing group of committed researchers, engineers, policy experts, and business leaders working together to build beneficial AI systems. We are looking for a Threat Collections Engineer to join our Threat Intelligence team. In this role, you will build the infrastructure that powers our threat discovery capabilities—integrating external data sources, developing detection systems for automated lead generation, and creating internal tooling that scales our investigators' impact. This is a foundational engineering role on a small, high-impact team. You will take projects from proof-of-concept to production, work closely with investigators to understand their needs, and help scale what may become a multi-person collections function.

Requirements

Have strong coding proficiency in Python and SQL for building detection logic, data pipelines, and automation
Have experience with data pipeline orchestration tools (Airflow, DBT, or similar)
Have familiarity with threat intelligence concepts including IOCs, YARA rules, and threat correlation techniques
Have experience integrating external APIs and building data ingestion systems
Can translate investigator needs and workflows into technical requirements
Are comfortable building v0 systems and iterating based on user feedback
Have strong communication skills for working closely with non-engineering stakeholders

Nice To Haves

Experience with threat intelligence sharing frameworks (e.g. MISP, STIX/TAXII)
Background in cyber threat intelligence, security operations, or abuse detection
Experience building MCP servers or similar tool integrations for AI systems
Familiarity with web scraping and data extraction at scale
Experience with behavioral analytics or anomaly detection systems
Understanding of LLM capabilities and how to leverage them for automation

Responsibilities

Build automated detection systems that use disparate signals to identify abusive behavior.
Take systems from idea to proof-of-concept to production-grade with appropriate monitoring, documentation, and maintenance processes
Develop and maintain YARA rule infrastructure, including tools for writing, validating, and testing rules against real data
Create integrations with external threat intelligence platforms (e.g. VirusTotal, Censys, Urlscan) via MCP servers to enable multi-source correlation during investigations
Build data pipelines that ingest intelligence from RSS feeds, CTI news sources, and partner sharing, using Claude to extract TTPs and generate targeted hunting queries
Develop behavioral analytics capabilities using DBT-based frameworks and create searchable audit logging infrastructure
Establish feedback loops with investigators to tune detection systems and reduce false positives
Scrape and normalize data from external sources to feed threat detection and enrichment workflows