Salary not listed
Software Engineer II - ADEX
AIWorkplace — unknown
Published on 2026-10-28
These details were extracted automatically from the original listing. They may not be complete or fully up to date — it's worth checking the original job post.
About this role
Own the design, launch, and operation of production detection systems focused on brand, lookalike-domain, VIP, and employee impersonation. The role combines security detection engineering, large-scale data analysis, and building and evaluating LLM-powered detection agents.
About the company
Abnormal Security uses AI to detect and stop email and collaboration attacks such as phishing and business email compromise. It protects enterprises against social engineering and account takeover.
The team
Advanced Detection of EXtended threats (ADEX), within Abnormal’s Detection org.
Stack
PythonSQLLLMsPostgreSQLDynamoDBRedisRocksDBKafka
What you'll do
- Design, build, launch, monitor, and maintain detection systems.
- Own ambiguous detection projects end-to-end, defining scope, risks, and milestones.
- Analyze missed attacks and translate patterns into detection improvements.
- Develop and tune detection logic and pipeline signals while minimizing false positives.
- Build and evaluate LLM-based detection agents using precision and recall metrics.
- Expose detection results as reusable intelligence for other products and teams.
- Participate in on-call, resolve escalations, and improve observability and runbooks.
- Use AI tools in development and contribute documentation and review feedback.
What we're looking for
- 3+ years of professional software engineering experience shipping and operating production systems.
- Strong software engineering fundamentals, including testing, debugging, and system design basics.
- Proficiency in Python and comfort learning new languages and frameworks.
- Comfort with SQL and analyzing large datasets.
- Adversarial or detection mindset and interest in studying real attacks.
- Experience using AI coding agents and enthusiasm for building LLM-powered detection.
- Ability to scope ambiguous projects, make tradeoffs, deliver reliably, and communicate clearly.
- Strong written and verbal communication, ownership, and growth mindset.
Nice to have
- Distributed systems, high-throughput pipelines, or large-scale data stores.
- Security, threat detection, anti-abuse, fraud, or trust-and-safety experience.
- ML or LLM evaluation, including precision/recall tradeoffs and evaluation tooling.
- Knowledge of DNS, typosquatting, homoglyphs, identity, or impersonation signals.
- Large-scale data tooling and distributed pipelines.
- Containerization, orchestration, or infrastructure-as-code experience.
- Frontend, ML, or MLOps experience.
- Experience in a fast-paced startup.