Join us in building the next generation of AI observability tools!
Responsibilities:
Build & ship features at high pace in a fast-moving AI development environment
Develop and maintain comprehensive observability tools for LLM applications and RAG systems
Create intuitive user interfaces for LLM tracing, evaluation dashboards, and production monitoring
Build robust APIs and backend services to support real-time LLM application monitoring
Collaborate with AI researchers and ML engineers to implement cutting-edge evaluation methodologies
Contribute to both frontend (React/TypeScript) and backend (Java) components
Design and implement automated evaluation systems and "LLM as a Judge" capabilities
Work on integrations with popular LLM frameworks and libraries
Participate in open-source community engagement and technical documentation
Requirements:
Experience: 3+ years of full-stack development experience, preferably in AI/ML domains
AI Development Tools: Hands-on experience with AI-assisted coding environments, IDEs, and agent-based workflows (e.g., Cursor, Windsurf, GitHub Copilot, Codex, Claude Code, and similar platforms)
Model Knowledge: Deep understanding of different AI model capabilities, limitations, and appropriate use cases (GPT-5, Claude, Gemini, etc.)
Frontend Development: Expertise in React, TypeScript and modern web development practices
Backend Development: Strong proficiency in Java with frameworks like Dropwizard
Database & Infrastructure: Knowledge of scalable database design and containerization
Observability Tools: Experience with tracing, monitoring, and evaluation systems
Collaboration: Strong communication skills for working in a distributed, global team environment
Problem Solving: Ability to work in ambiguous environments and solve complex technical challenges
Nice to have:
Open Source: Experience contributing to or maintaining open-source projects
AI/ML Experience: Understanding of Large Language Models, RAG systems, and AI application architectures
Preferred Qualifications:
Experience with model evaluation, prompt engineering, and LLM optimization
Knowledge of distributed systems and high-throughput data processing
Familiarity with ML experiment tracking and model monitoring platforms
Experience with DevOps practices and CI/CD pipelines
Understanding of AI safety, model security, and responsible AI practices
What We Offer:
Competitive salary, based on proven experience, skills and location.
Competitive benefits package.
Flexible working hours and remote/Hybrid work options.
Opportunities for professional growth and development.
A collaborative and innovative work environment.
The chance to work with cutting-edge technologies and projects.
This role will be located in Tel Aviv, Israel (with hybrid flexibility) or in Europe (fully remote), working with a global team (large presence in the US, Tel Aviv and Europe), some flexibility with work hours is required to collaborate across time zones.
Comet is an equal-opportunity employer. We celebrate diversity and are committed to creating an inclusive environment for all employees without regard to race, religion, color, sex, gender identity, gender expression, sexual orientation, national origin, ancestry, citizenship status, uniform service member status, marital status, pregnancy, age, medical condition, physical or mental disability, genetic information/characteristics, and any other characteristic protected by State or Federal law.
