Voice Ops

OVERVIEW

Our company is predicated on the idea that the richest dataset companies own — recorded customer conversations — is also the most difficult to tap into.

That's because human conversations are messy. Previous software attempts at structuring conversation data leave a lot to be desired.

We are taking the same approach to conversation analysis that Uber/Cruise/Waymo are taking for self-driving cars. Building troves of training data, and solve lots of edge cases piece by piece towards the goal of having an incredibly reliable system that makes sense of human conversations.

Our core technical challenge is how to take billions of audio recordings (and messy, unstructured human conversations) and make sense out of that data in a way that is: a) accurate b) cost efficient, and c) highly scalable.

(The corresponding product problem is how to take well-structured data and make it actionable for the end-user)

WHY JOIN US

Impact: the team is small, you’ll help set the template for engineering quality and process. You'll also be encouraged to contribute to product decisions, and help shape the direction of the company.

Stellar Team and Culture: We have very high standards for our engineering team, so you'll get to work with some of the smartest people you've ever worked with.

Growth: We've just raised our Series A and are looking for more smart people to continue growing quickly. You’ll be one of the first few employees and have opportunities to be a leader on a growing team.

PROJECTS YOU COULD WORK ON

Comments: a project which lets our users have dialog while on VoiceOps (similar to Google Docs), allowing feedback to be focused on specific moments in calls. This is a typical product feature where the engineer(s) working on it would own the data model, API design, and frontend implementation.

State machine: Implementation of a robust, configurable, thread-safe state machine to move calls through various analysis steps, with visibility if any of the steps are slow or failing. Before this project, calls could go through the same step multiple times or be processed out of order due to stale object references or multiple threads executing at once.

Integrations: integration system which imports call recordings from dozens of customer systems, supporting the analysis of thousands of calls per day. Challenges include failure visibility, networking/VPN constraints within customer data centers, and careful handling of timezones / date cutoffs with international customers.