What You’ll Do
- Create goal-oriented AI agents capable of planning and executing multi-step security assessments.
- Contribute to an AWS-native framework for complex security testing workflows.
- Integrate cutting-edge LLM models and cybersecurity tools into the framework.
- Customize solutions to address specific customer pain points and security challenges.
- Continuously refine and expand the capabilities of the autonomous security testing system.
Required Experience
- 4+ years of software engineering experience with world class teams
- Programming Languages: Proficient in Python or Javascript / Typescript.
- Large Language Models (LLM) Frameworks: Practical experience with at least one of the popular frameworks such as:
- LangChain: For building applications with large language models.
- LlamaIndex: For developing and deploying language models.
- AutoGen: For creating agentic workflows.
- Prompt Engineering: Skilled in crafting effective prompts to optimize the performance of language models and enhance AI-driven applications.
- RAGs: Hands-on experience in building and deploying RAG systems.
- Vector databases: for storing and querying embeddings and building RAGs.
- API Development: Expertise in designing and implementing RESTful APIs to facilitate communication between different components of the AI system.
Bonus Points Experience
- AWS experience: Familiarity with S3, Lambda, and DynamoDB for scalable and efficient deployment of AI solutions.
- Cybersecurity experience: Experience as a Red Teamer, Penetration Tester, or Security Engineer.
- Database Design: Experience with NoSQL databases, such as MongoDB or DynamoDB, for efficient data storage and retrieval.
