Senior Software Engineer, Voicebox

Stardog, the leading Enterprise Knowledge Graph platform, turns data into knowledge to power more effective digital transformations. Industry leaders including Bosch, NASA, and Raytheon use Stardog to create a flexible data layer that can support countless applications. One of Fast Company's prestigious Most Innovative Companies, Stardog is a fast-growing venture-backed company with a globally distributed team.

As a Senior Engineer on the Voicebox team you will be working on the frontier of the Stardog Product. Voicebox is the most recent addition to Stardog and is an agentic system running on top of our world-class Knowledge Graph Platform. Voicebox is able to turn natural language questions and objectives into multi-step plans, fetching data from multiple locations, both structured and unstructured, providing a complete, hallucination-free answer.

We are looking for someone to help us scale the Voicebox architecture. Experience with LLM's particularly experience fine-tuning and even training models would be great. You should have extensive prompt engineering experience and have built product capabilities on GenAI before and understand how LLMs work.

We're looking for experience with Python, but have no strong allegiances in the GenAI ecosystem. LlamaIndex, LangChain, Crew, every day there's more libraries. We're happy for you to have extensive experience with any of them.

Equally important, we're looking for experience building large scale systems; Voicebox will be the backbone of tens of thousands of knowledge workers in large enterprises, consuming information from hundreds of structured systems and thousands of unstructured documents, to provide its answers.

We'd love to see familiarity with big data technology like Spark, Airflow, Flink, and others. Experience with Java is a nice bonus. The Platform is written in Java and you may be responsible for adding new features to support Voicebox.

While we would love to see a Computer Science, Software Engineering or related degree, we simply want good engineers who will work hard to solve interesting problems. Solid knowledge of data structures, algorithms and software design and a dedication to the craft is all that's really required.

We are a remote-first company. You should be comfortable with, and have experience working remotely. You must have strong communication skills as much of our interactions will be over email, chat, and PR where it's harder to get your point across.

And if you've had previous experience with graph-based technologies, in particular, the semantic technology stack, that's fantastic! If not, we'll welcome you to the world of graph, and the future of enterprise data management.

If you want to learn about the kinds of scale challenges we're building for, read about our Trillion Edge graph. And If you are curious about what it's like to work here, check out a post from our CTO and co-founder that talks about our culture, or read the engineering team's blog.

Lastly, you'll get great benefits, a yearly continuing education stipend, flexible PTO options, and the ability to work whenever and wherever you prefer.

Our culture is based on engineering excellence, mutual respect, collegiality in all things, rigor in design, research, implementation, and testing. We care deeply about work-life balance and productivity in the short and long run. In sum, if you remove the unnecessary, the distracting, and the tedious, what you're left with is a healthy 40 hour week full of wins.