Software Engineer, Retrieval

Who We Are

Our mission at Capacity is to help teams do their best work through our AI-powered support automation platform. Capacity provides everything you need to automate support and business processes in one powerful omni-channel platform.

We believe that each individual voice, perspective and background brings inherent value to enhance our product, serve our customers and generate more ideas to solve complex problems. By continuing to hire talented, driven and humble teammates, we have the opportunity to see Capacity become a premier brand enterprise SaaS platform.

Capacity has raised over $100 million dollars from over 150 investors, giving us the opportunity to make ambitious investments in our team and big bets on our future. Our total addressable market is enormous. Any company that wants to grow revenue, reduce costs, and improve customer and employee satisfaction is an opportunity for Capacity to shine.

Why this job is exciting

The Role

Capacity builds a powerful customer experience automation platform, of which one of the core features is our agent orchestration layer. In order to ensure that those agents use correct and up-to-date information, we are improving our retrieval layer for surfacing relevant knowledge to them, and are looking for a Software Engineer to join our team and help improve the quality and responsiveness of our retrieval layer.

Responsibilities

In this role, you will be responsible for the following:

• Gather and generate data for evaluating and improving search quality and propose algorithm changes based on those evaluations
• Move prototype functionality to production
• Create and manage generative AI pipelines for improving search index quality
• Setup and maintain retrieval models and their infrastructure
• Implement feedback mechanisms to use user and agent interactions for improving retrieval quality
• Improve retrieval throughput and latency

Most importantly, you’re not afraid to ask for help and are proactive in offering it. You share your own knowledge and are always trying to learn what needs to be done to take things to the next level.

Note that the listed responsibilities are not meant to be exhaustive; these represent just some of the anticipated duties and/or functional areas that you may be expected to perform along with other new tasks that may arise.

Requirements

• 3+ years of experience working in a software engineering environment. Able to use version control and project management software (git, JIRA)
• Experience with full-text search (ideally elasticsearch) and modern retrieval models (ideally Huggingface)
• Backend development
• Python, pytorch and dataframe processing libraries (pandas or polars)
• Experience with one modern statically typed programming language (e.g. Scala, Kotlin, Java, Go, Rust, C#, C++, Swift, TypeScript, Haskell). Our backend is written in Scala and Java
• Experience working with LLM APIs

Additional Technical Skills (preferred)

• Natural Language Processing
• Graph retrieval and knowledge graphs
• SQL
• Data cleanup and training data generation
• Backend web development
• Kubernetes
• ML Inference runtimes
• Apache Spark
• AI Coding tools such as Claude or Codex

You Are Motivated By

• Hustle: You inspire others to work as hard as you. You will find a way, no matter how hard the task is.
• Ownership: You have an owner/builder mentality. You care about what you deliver and own your mistakes.
• Proactivity: You don’t wait for someone to tell you what to do or what problems to solve. You are always looking for ways to learn and improve.
• Excellence: You set a high bar and surpass expectations. You hit your goals and ask for more.
• Humility: You are not above any task in the organization and are willing to drop what you’re doing to help a teammate.

The Team

What you can expect from us

Capacity team members enjoy the opportunity and benefits of working at an artificial intelligence startup, but with leaders who’ve worked at places like Apple, Ebay, Visa, Answer.