Our client is a leading cybersecurity company specializing in exposure management and security validation. Founded in 2016 by an elite team of former IDF intelligence officers and cyber researchers, their mission is to empower organizations worldwide to proactively test and optimize their security posture against the evolving threat landscape.
Key Responsibilities:
- Design, build, and refine LLM agents capable of reasoning and executing complex tasks
- Implement and integrate LLMs (GPT, Claude, Mistral, etc.) with multi-agent frameworks like Langgraph, Langfuse, etc.
- Improve agent reasoning, long-term memory, and real-world adaptability
- Write efficient, maintainable, and scalable Python-based AI systems
- Work with APIs, vector databases, and cloud services to integrate AI agents into production environments
- Improve response times, fine-tune models, and enhance overall system robustness
- Work closely with ML researchers, engineers, and product teams to drive AI advancements
Requirements:
- 4+ years of experience in Python
- Hands-on experience building AI agents, LLM applications, or automation tools
- Strong understanding of AI reasoning, planning, and execution frameworks
- Experience working with LLMs, APIs, and vector databases
- Strong debugging, problem-solving, and performance optimization skills
Would be a plus:
- Experience with Kubernetes
- Knowledge of cloud services (AWS, GCP, Azure) & deployment strategies
What We Offer:
- Startup culture, a strong goal-oriented team, and a research mindset
- Opportunity to leverage your engineering skills for fellow engineers and shape the future of AI
- Working with the newest technical equipment
- 20 working days of annual vacation leave
- English courses, Educational Events & Conferences
- Medical insurance