At Helicone.ai, we’re building the premier platform for LLM (Large Language Model) observability, empowering developers and data scientists with real-time insights and optimizations for their AI-powered applications. Our mission is to bridge the gap between complex AI systems and operational efficiency, providing tools that make it easier to track, analyze, and fine-tune LLM applications at scale.

Why Helicone?

• Open Source Community:
  We are deeply committed to user-centric development and transparency. Our open-source platform thrives on community-driven innovation, ensuring every contribution shapes the future of AI observability.

• Purpose-Built for LLM Developers:
  Designed by LLM developers for LLM developers, our tools streamline every aspect of building, deploying, and scaling LLM applications. From custom properties to caching, Helicone provides tailored solutions to enhance your workflows.

• Right Time, Right Space:
  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, and joining us now means you’ll play a pivotal role in shaping this journey.

Culture at Helicone

Our HQ is in the heart of San Francisco, the hub of AI innovation, and our culture reflects the dynamic, fast-paced energy of the industry.

• Collaborative and Fun:
  Every idea is heard and encouraged, fostering a creative and supportive work environment.

• Team Building:

  • Weekly Team Lunches: Connect over food and celebrate wins together every Thursday.
  • Monthly Hackathons: Collaborate on creative side projects and compete for mini prizes in a fun, hands-on environment.

• Flexibility and Autonomy:
  We trust our team to deliver and offer remote work options and flexible hours to balance productivity with personal time.

What We Value

• Technical Excellence:
  We thrive on building efficient, maintainable systems. Engineers here take ownership of their projects from end to end.

• Growth Mindset:
  Helicone is a place to solve complex challenges, learn from peers, and continuously improve your craft.

• Adaptability:
  As a fast-growing startup, we pivot and iterate quickly. We value team members who excel in dynamic environments.

Perks & Benefits

• Career Development: Opportunities for mentorship, technical ownership, and building a legacy in the LLM space.
• Competitive Compensation: Includes equity, allowing you to share in the company’s growth.
• Team Bonding: From hackathons to lunches, we foster an environment where collaboration and fun go hand in hand.

Interested in Building the Future of AI?

As a founding engineer at Helicone, you’ll work closely with the founders and team to build scalable systems, solve critical challenges, and own impactful engineering projects. Join us and make your mark on the rapidly evolving LLM space.

Are you a skilled engineer looking to level up and make a substantial impact in AI observability? Helicone.ai is seeking a technically proficient, highly driven software engineer to join our team. We’re an agile startup developing a platform for LLM observability, helping developers gain insights, optimize performance, and streamline workflows in AI applications.

What We’re Looking For:

This role requires a mid-level software engineer who’s a problem-solver at heart and passionate about building scalable, resilient systems. You'll be working closely with our engineering team to shape the future of LLM observability.

Key Responsibilities:

• Design, build, and optimize microservices, ensuring they’re maintainable, scalable, and aligned with our architectural standards.
• Collaborate on developing new features in TypeScript, Node.js, and Python, optimizing for both performance and readability.
• Build and maintain integrations with LLM providers like OpenAI, Anthropic, and LangChain, enabling seamless data tracking and analytics.
• Work with Next.js to develop our frontend components, enhancing usability and performance for complex observability metrics.
• Contribute to data processing workflows using tools like Clickhouse, Kafka, or similar distributed data systems.

Ideal Candidate Profile:

• 3-5 years of experience in software engineering, with a deep understanding of backend services and a solid grasp of frontend fundamentals.
• Proficiency in TypeScript and Node.js, with experience building RESTful APIs.
• Strong foundation in distributed system design, with knowledge of data processing at scale.
• Familiarity with Next.js or similar React frameworks.
• Experience with observability tools and methodologies, such as monitoring, tracing, and logging.
• Working knowledge of Docker, Helm, or other container orchestration tools.
• You prioritize code quality and performance optimization in everything you build.

Why Helicone?

• Impact: Join a small, focused team where your contributions directly influence the product’s direction and success.
• Growth: You’ll work with and learn from highly skilled engineers and have opportunities for mentorship and technical ownership.
• Technology Stack: Our stack includes TypeScript, Node.js, Next.js, Clickhouse, Supabase, and Kubernetes, with integrations across leading LLM SDKs and frameworks.
• Competitive Benefits: We offer a compelling package, flexible work hours, and remote work options.

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

• Languages: TypeScript and Python power our core platform, offering flexibility and reliability for both backend and data-intensive tasks.
• Frameworks: Next.js, React, Tailwind CSS, Express, and ShadCN form the foundation of our user-facing and backend systems, delivering seamless performance and intuitive interfaces.
• Hosting: We deploy across Kubernetes, AWS, GCP, Vercel, and Supabase, ensuring scalability and flexibility to meet diverse deployment needs.
• Services: Core components include Docker, Postgres, Clickhouse, Cloudflare Workers, and Redis, which together enable efficient data storage, processing, and caching for high-throughput systems.
• LLMs: Our platform supports a variety of large language models, including OpenAI, Anthropic, Gemini, TogetherAI, and more, ensuring compatibility and flexibility for developers.
• Developer Tools: We rely on Unix, CLI, and git to maintain a robust development workflow.

Challenges We’re Tackling

1. Real-Time Observability at Scale:
   Building a platform that processes millions of events in real time requires highly optimized data pipelines. With Clickhouse and Redis, we ensure low-latency data ingestion and querying to deliver actionable insights instantly.

2. Unified LLM Integrations:
   Supporting multiple LLM providers means creating unified abstractions that simplify diverse APIs. Developers can seamlessly integrate and switch between providers like OpenAI, Anthropic, and Gemini without additional overhead.

3. Prompt Management and Experimentation:
   We empower developers to track prompt versions, run experiments, and analyze metrics like cost, latency, and accuracy. This enables fine-tuned optimizations to improve performance and ROI for LLM applications.

4. Data Privacy and Security:
   With enterprise customers relying on our platform, we maintain SOC 2 and GDPR compliance while implementing features like rate limiting, access control, and secure caching to safeguard sensitive data.

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!