Helicone is the open-source observability platform for LLM applications. We provide developers with the monitoring, optimization, and reliability tools they need to build production-ready AI systems. From real-time insights and intelligent routing to comprehensive analytics, Helicone gives engineering teams complete visibility into their LLM stack.

We're deeply committed to open source and transparency. With 4k stars and a thriving community, we believe the best developer tools are built in the open. Our platform includes both our core observability suite and our lightweight Rust-based AI Gateway, providing everything teams need to scale their LLM applications reliably.

This is the right time to join us. The LLM ecosystem is rapidly evolving, and in 5 years, there will be unicorns and giants in this space. We're on track to becoming one of them, growing ~20% MoM over the past year. Joining us now means you'll play a pivotal role in shaping the future of AI infrastructure.

Culture at Helicone

Ship mentality: We build efficient, maintainable systems and take ownership from end to end, while prioritizing shipping and speed to get products out to market.

Growth Mindset: We solve complex challenges, learn from peers, and continuously improve.

Adaptability: As a fast-growing startup, we pivot and iterate quickly in dynamic environments.

Perks & Benefits

• Competitive compensation with meaningful equity
• Comprehensive health benefits
• Career development opportunities in the rapidly growing AI infrastructure space
• Team building through hackathons and collaborative environment.

We're looking for someone who's as excited about this space as we are and wants to build something transformative together.

As a Founding Engineer at Helicone.ai, you’ll work side-by-side with the founders and a passionate team to build highly scalable systems and own end-to-end engineering projects that redefine the LLM developer experience. This is a unique opportunity to be part of a founding team, shape a product from the ground up, and make an outsized impact on the future of AI observability.

Why Join Helicone?

This is more than just a role—it's an opportunity to build something transformative at the ground level. You’ll be joining a tight-knit, ambitious team in San Francisco, the heart of AI innovation, and contributing to the leading platform for LLM observability.

• Ownership and Impact: Your work will directly shape the platform, the team, and the company’s future.
• Dynamic Culture: Weekly team lunches, monthly hackathons, and an environment where every idea is heard.
• Growth Opportunity: Work on cutting-edge problems in AI, learn from the founders, and develop skills that push the boundaries of engineering.

If you’re looking for a challenging, impactful role where you can grow alongside a team that’s redefining observability for AI, we’d love to hear from you.

Key Responsibilities

• Build Features: Design and implement new software features that enhance Helicone’s platform and developer experience.
• Develop and Maintain Backend Services
  • Frontend services (NextJS/Tailwind)
  • Proxy worker (Wrangler/Cloudflare)
  • Application database (Supabase)
  • Analytics database (ClickHouse)
  • Backend Services (Expres/AWS ECS)
  • Queue (Kafka)
• Own Projects End-to-End: Take responsibility for features and systems, from ideation to deployment and beyond.
• Deployment and Operations: Manage and streamline deployment processes to ensure smooth operations.
• Collaborate and Contribute: Work on feature requests, integrations, and documentation improvements to enhance usability.
• Engage with the Community: Actively gather feedback, foster contributions, and improve the developer experience based on real-world insights.

Preferred Skills

• Proficiency in TypeScript: With 91% of Helicone's codebase in TypeScript, deep experience is essential.
• Experience with SQL or Similar: Strong database skills for working with ClickHouse, Supabase, and Postgres.
• Cloud Services Expertise: Familiarity with cloud deployment workflows; experience with Cloudflare is a plus.
• Problem-Solving and Communication: A clear thinker who can break down complex problems and communicate effectively.
• Adaptability: A fast learner who thrives in a dynamic environment with evolving challenges.
• AI Awareness: Solid understanding of LLMs and the current AI landscape.
• Helicone Familiarity: Must have tried the platform at least once—your hands-on experience will be invaluable.

Helicone Tech Stack

• Languages: TypeScript, Python
• Frameworks: Next.js, Tailwind CSS, Express, ShadCN
• Hosting: Kubernetes, AWS, GCP, Vercel, Supabase
• Services: Docker, Postgres, ClickHouse, Cloudflare Workers, Redis
• Developer Tools: Unix, CLI, git
• LLMs: OpenAI, Anthropic, Gemini, TogetherAI, and more

Helicone Tech Stack and Challenges

At Helicone.ai, we combine a cutting-edge tech stack with a focus on solving complex problems in AI observability. Our platform is designed to give developers unparalleled insights into their applications' performance, costs, and behavior, all while being scalable, developer-friendly, and secure.

Tech Stack

Frontend: TypeScript, Next.js, React, Tailwind, ShadCN Backend: Python, Express, Postgres, Clickhouse, Redis Infrastructure: Kubernetes, AWS, GCP, Vercel, Supabase, Cloudflare Workers LLM Support: OpenAI, Anthropic, Gemini, TogetherAI, and more

Challenges We’re Tackling

1. Real-Time Observability at Scale: Processing and querying millions of events through Clickhouse and Redis pipelines.

2. Unified LLM Integrations: Abstractions across OpenAI, Anthropic, and Gemini for easy provider switching.

3. Prompt Management and Experimentation: Version control and experimentation tools to track costs, latency, and accuracy.

4. Data Privacy and Security: With enterprise customers relying on our platform, we maintain SOC 2 and GDPR compliance with rate limiting, access control, and caching.

By joining Helicone, you’ll dive into some of the most exciting challenges in AI observability, from real-time analytics to developer-centric tooling. Our dynamic team is shaping the future of AI performance monitoring, and we’d love for you to be part of it!