Ravenna is an AI-native internal help desk deeply integrated with Slack. Our platform automates service requests, knowledge base management, and common help desk tasks, providing comprehensive performance metrics. We're disrupting the ITSM market with AI that works.
If you work at a company that uses Slack, chances are you've used a wide range of #help, #ask, or #support channels. These are places where you go to request help from your colleagues. Whether you need assistance resetting your password or finding the latest sales enablement content, these channels are critical for quickly getting the information you need so you can get back to doing what you love.
These channels are the modern help desk. They are the oil in the gears of the modern, chat-centric organization.Behind the scenes, they need software that allows people to turn questions into trackable, assignable, and resolvable tickets. For those operating these help channels, robust performance metrics are also essential. Increasingly, they want AI to answer tickets for them and resolve their colleagues' questions faster. Ravenna is that software platform.
If you're passionate about creating outstanding software that delights users, using cutting-edge technology, and tackling ambitious challenges, we'd love to discuss opportunities at Ravenna with you.
About the role At Ravenna, we're looking for experienced engineers with a passion for AI/ML and a proven track record in full-stack engineering. We're combining the latest in LLMs along with the best-in-bread ML techniques to create delightful and modern product experiences. If you have 5+ years of experience and are excited about leveraging cutting-edge technologies to disrupt old/huge markets, we want to talk to you.
About You You can speak fluently about transformer networks, attention mechanisms, and how they contribute to the models' abilities to generate coherent responses, generate function calls, and perform other language tasks.You have worked with LLMs to perform complicated tasks in production environments. You're familiar with advanced prompt techniques for LLM grounding such as chain-of-thought, zero-shot, and dynamic few-shot.You're proficient in deploying evaluation frameworks for LLMs, focusing on performance, reliability, and bias assessment.You have experience with Retrieval-Augmented Generation ('RAG') systems and how to optimize knowledge retrieval for improved model accuracy and speed.You have a deep understanding of different indexing/chunking strategies based on the data and goal of the system. Understanding of semantic search and vector databases, and how they differ from classic retrieval methods and databases.You have a track record of working through the full lifecycle of building, testing, deploying, and scaling LLM architectures.How to Apply Reach out to us at ****** . Send your resume along with a short description of the most interesting AI/ML project you've worked on.
#J-18808-Ljbffr
