LLM Engineer
As a foundational LLM Engineer, you will take end-to-end ownership of building and deploying AI Agents and LLM systems in production. You'll architect scalable Agentic AI workflows, develop FastAPI microservices, and ensure low-latency, reliable execution of generative AI models on AWS. Work in a core AI squad in a hybrid Tel Aviv environment.
Responsibilities
- Build and deploy AI Agents and LLM systems in production environments.
- Architect scalable Agentic AI workflows, orchestration pipelines, and memory management.
- Develop robust backend microservices using FastAPI and AWS.
- Design and optimize prompt pipelines for classification and summarization tasks.
- Ensure system reliability, low-latency execution, and continuous performance evaluation of generative AI models.
Requirements
- B.Sc. in Computer Science, Software Engineering, or equivalent IDF elite unit background.
- 3+ years of software development experience.
- 1+ years of AI/GenAI/LLM engineering experience.
- Proven experience in fast-paced startup environments.
- Proficiency in Python, FastAPI, and AWS.
Nice to have
- Hands-on experience building AI Agents/Agentic Workflows (tool use, orchestration, memory, prompt engineering, evaluation).