As a Full Stack Engineer, you will build systems that power a dynamic, ever‑evolving automated red teaming framework and sandboxing for GenAI models with a focus on LLMs, and the pipelines that evaluate those prompts across providers.

We’re looking for a product‑minded, hands-on developer who is comfortable moving from frontend UX to backend services and has a familiarity with GenAI apps.

Key Responsibilities

• Build prompt management, versioning, and metadata services
• Implement evaluation runners that execute prompts against multiple model backends (Hugging Face, Amazon Bedrock, Azure) and collect metrics, logs, and failure cases.
• Create analytics dashboards and APIs to compare guardrail effectiveness across models, policies, and releases.
• Design reliable, secure AWS workloads (Lambda, S3, EC2, Step Functions) and SQL pipelines (Athena/Redshift) for data ingestion and reporting.
• Ship production‑quality code end‑to‑end: tests, CI/CD, observability, and documentation.
• Collaborate with AI security researchers to translate red‑team findings into productized workflows aligned with frameworks such as OWASP AI Security, MITRE ATLAS, and NIST AI RMF
  
  

Requirements:

Must-Have

• 3+ years programming in Python, React, Node.js/FastAPI
• Experience with AWS (Lambda, S3, EC2; bonus: Step Functions, EventBridge).
• Experience in SQL and data modeling; advantage: Redshift or Athena.
• Demonstrated experience across both frontend and backend development
  
  

Nice-to-Have

• B.Sc in Computer Science, Electrical Engineering, Mathematics, or related field.
• Hands-on‑on with Agentic AI frameworks (LangChain, AutoGen) and protocols (MCP, A2A).
• Background in content safety, abuse prevention, or adversarial testing.
  
  

About ActiveFence:

ActiveFence is the leading provider of security and safety solutions for online experiences, safeguarding more than 3 billion users, top foundation models, and the world’s largest enterprises and tech platforms every day.

As a trusted ally to major technology firms and Fortune 500 brands that build user-generated and GenAI products, ActiveFence empowers security, AI, and policy teams with low-latency Real-Time Guardrails and a continuous Red Teaming program that pressure-tests systems with adversarial prompts and emerging threat techniques. Powered by deep threat intelligence, unmatched harmful-content detection, and coverage of 117+ languages, ActiveFence enables organizations to deliver engaging and trustworthy experiences at global scale while operating safely and responsibly across all threat landscapes.