Senior Software Engineer

About Elicit

Elicit is an AI research assistant that uses language models to help researchers figure out what’s true and make better decisions, starting with common research tasks like literature review.

What we're aiming for:

1. Elicit radically increases the amount of good reasoning in the world.
   

   • For experts, Elicit pushes the frontier forward.

   • For non-experts, Elicit makes good reasoning more affordable. People who don't have the tools, expertise, time, or mental energy to make well-reasoned decisions on their own can do so with Elicit.

2. Elicit is a scalable ML system based on human-understandable task decompositions, with supervision of process, not outcomes . This expands our collective understanding of safe AGI architectures.

Visit our Twitter to learn more about how Elicit is helping researchers and making progress on our mission.

Why we’re hiring for this role

Since launching the newest version of Elicit last fall, response has been strong. We introduced Elicit Plus, our monthly subscription plan, and added thousands of paying users in a matter of months as well as hundreds of thousands of new sign-ups. This has been energizing for our team, but we want to ship more useful functionality to our users even faster. We want to add another strong senior-level engineer to our team who’ll help us meet the demand for new features and improved performance.

Our tech stack

• Backend: Node and Python

• Frontend: Next.js, TypeScript, and Tailwind

• We like static type checking in Python and TypeScript

• All infrastructure runs in Kubernetes across a couple of clouds

• We use GitHub for code reviews and CI

Am I a good fit?

Consider these questions:

1. What are a couple of different ways to write concurrent code in Python?

2. What are the differences between var , let , and const in JavaScript?

3. What are a couple of different web technologies to asynchronously send data from a server to a client?

4. In which situations would you use REST vs. GraphQL vs. RPC?

Strong applicants will find it easy to answer these questions.

Location and travel

We have a lovely office in Oakland, CA, but we don't all work from there all the time. It's important to us to spend time with our teammates, however, so we ask that all Elicians spend 1 week out of every 6 with teammates.

• We have a quarterly team retreat, normally in and around the SF bay area.

• We have quarterly co-working weeks (offset from the team retreats) in our Oakland office.

• If you come to the retreats and co-working weeks, you'll meet our expectations for in-person time!

• There is flexibility around the specifics here: if you're not sure you can make this work, get in touch.

What you'll do

You'll own:

• Building Elicit into a product researchers can’t live without

  • You’ll fully own shipping useful, exciting features out to users on a weekly basis.

  • You will work on a mix of known features / fixes, prototypes to validate ideas, and exploratory projects in between.

  • Our team is small, so we expect you to appreciate the user needs underlying everything you work on. You should be comfortable making decisions and trade-offs that help us fulfill users’ needs best.

• Keeping Elicit’s bar for quality high

  • You’ll balance shipping features in the short term with building extensible and maintainable systems.

  • You will be responsible for your features in production: they need to be scalable, resilient, and easy to operate.

  • You’ll contribute to discussions around UX, system design, and architecture.

Projects you'll contribute to:

Your first week:

• Start building foundational context

  • Get to know your team, our stack, and the product roadmap.

  • You’ll get to know our company documentation and other supporting resources like Supporting Process, not Outcomes .

• Make your first contribution to Elicit

  • By the end of your first week, you’ll have completed your first Linear issue, have a PR merged into our monorepo, gained understanding of our CI/CD pipeline, and learned about our monitoring and logging tools.

Your first month:

• You’ll complete your first multi-issue project

  • As you learn the ropes, you’re able to tackle more impactful projects, with input from domain experts where you need it.

• You’re actively improving the team

  • You’ll have gotten into the swing of contributing to regular team meetings and hack days, and you’ve demoed something you’ve worked on during a team sync.

  • You’ve added some documentation, how-to guides, diagrams, or other resources meant to help us and new hires in the future.

  • You’ve suggested an improvement to our development process.

Your first quarter:

• You’re flying solo

  • With the context you’ve gained, you’re able to implement changes independently and you’re comfortable making big, impactful decisions in the course of your work.

• You’ve developed an area of expertise

  • Our engineering team is just a few people, so each person quickly becomes a go-to resource in some area of the tech. Within your first quarter, we expect that there’s a part of Elicit you’ll become the domain expert for that others reach out to for support when working in this area.

• You actively research and improve the product

  • By the end of your first quarter, you’ll have gotten to know Elicit and our users well. We expect that you’ll have thought about and scoped some user-facing improvements to the product as well as identified technical improvements to implement.

What you bring to the role

• Strong technical aptitude that allows you to move comfortably around our tech stack, both back-end and front-end, with strong computer science fundamentals.

• Professional experience contributing to software development teams at a mid-career to senior level. We’re excited for you to unpack your past successes and build off your previous experience at Elicit!

• Above-average communication skills. Elicit is a small, highly-collaborative team, so you’ll frequently be tapped to communicate complex engineering topics with stakeholders across the company.

• Your past experience or exposure to working with language models. Because of the way language models work, you’re used to writing a lot of asynchronous code and thinking defensively about error handling.

• A sense of joy in what you do. One thing we love about our team at Elicit is that everybody’s a craftsperson who cares deeply about their field.

Who you’ll work with

This role will report directly to James , our Head of Engineering, and work very closely with the rest of the engineering team:

• Luke (Full-stack Engineer)

• Panda (Infra Engineer)

• Justin (ML Engineer)

You'll also spend a lot of time collaborating with Product Designers, Kevin (Head of Product), and co-founders Jungwon & Andreas .

Compensation, benefits, and perks

In addition to working on important problems as part of a productive and positive team, we also offer great benefits (with some variation based on location):

• Flexible work environment: work from our office in Oakland or remotely with time zone overlap (between GMT and GMT-8), as long as you’re comfortable traveling for in-person retreats and coworking events

• Fully covered health, dental, vision, and life insurance for you, generous coverage for the rest of your family (FSA/HSA, too)

• Flexible vacation policy, with a minimum recommendation of 20 days / year and plenty of company holidays

• 401K with a 6% employer match

• $2,000 device budget to start, with more accumulating for each month of work

• $500 / year personal development budget

• A team administrative assistant who can help you with personal and work tasks

• You can find more reasons to work with us in this thread !

For all roles at Elicit, we use a data-backed compensation framework to keep salaries market-competitive, equitable, and simple to understand.

• This role starts between $195-230K + equity, depending on your level. We're optimizing for a hire who can contribute at a L4/senior-level or above.