LLM Engineer (AI)

An established, successful technology startup that develops an AI-native SaaS platform for high-scale cybersecurity automation.

Operating with a team of roughly 100 employees, the organization integrates cutting-edge artificial intelligence with cloud infrastructure to protect modern distributed networks.

The company is located in Tel Aviv (conveniently accessible via both the train and light rail stations) and operates on a hybrid model of two days office-based.

Key Responsibilities-

• Writing clean, maintainable, and highly optimized production code in Python to orchestrate advanced multi-agent AI workflows.
• Designing and implementing robust prompt engineering strategies, retrieval-augmented generation (RAG) pipelines, or model fine-tuning frameworks.
• Building and scaling high-throughput API endpoints that facilitate low-latency communication between web clients and distributed AI services.
• Integrating custom evaluation frameworks to monitor, log, and prevent model drift, hallucinations, or adversarial vulnerabilities within the AI layer.
• Translating complex technical requirements from threat-intelligence analysts into automated, deterministic software solutions.

Requirements-

• 4+ years of professional software engineering experience centered on production-grade systems design (Mandatory).
• Proven hands-on production experience developing and deploying LLM-based applications, agentic frameworks (e.g., LangChain, LlamaIndex), or advanced generative AI pipelines (Mandatory).
• Strong, production-level backend development proficiency utilizing Python (Mandatory).
• Demonstrated experience building and optimizing scalable web architectures, specifically designing REST APIs (Mandatory).
• Deep structural familiarity or direct practical experience operating with a diverse set of open-source and commercial AI models is a significant professional advantage.