Location: Remote worldwide; business trips to Israel may be required.
Company
V4Scale enhances the R&D capabilities of Israeli and US technology firms through a global remote workforce and projects for technology startups.
What you will do
•Build production LLM-powered applications and AI agents for a leading Israeli startup operating in stealth mode.
•Implement agent orchestration, tool calling, retrieval-augmented generation, and context management.
•Optimize latency, token usage, and application cost.
•Develop LLM evaluation, observability, and model-routing capabilities.
•Build and operate multi-agent systems using vector databases and production runtime environments.
•Deploy and maintain containerized services on Google Cloud Platform and Kubernetes.
Requirements
•5+ years of Python development experience.
•Strong React and TypeScript skills.
•Hands-on experience building production LLM applications and AI agents, including orchestration, tool calling, RAG, context management, latency, token usage, cost optimization, LLM evaluation, observability, and model routing.
•Strong experience with LangGraph, LangChain, or LlamaIndex, as well as multi-agent systems and vector databases.
•Strong hands-on experience with Google Cloud Platform, Kubernetes, containerized deployments, and production runtime environments.
•English at B2+ level.
Culture & Benefits
•Remote work with a mixed international team.
•Flexible working hours.
•Work with cutting-edge technologies on a project suitable for professional portfolios.
•High salaries and bonuses.
•Business trips to Israel with a beach hotel and rented car.
•Experienced mentors and a friendly team environment.
