We're a deep-tech company doing hard science and solving difficult problems on both the technical and science side.
Wherever possible, we avoid reinventing the wheel. If you've come hoping to build the next JS framework or cloud platform, you're in the wrong place. Our stack consists of tried and tested products. That said, if you feel like a particular tool would really help us solve a problem, we’re totally open to experimenting!
We're trying to work with huge datasets to create human-understandable solutions to very complex problems, and are pushing the boundaries of ML and AI as a result. The number of proteins in our search space is larger than the number of elementary particles in the known universe - searching that vast array of possibilities requires cutting-edge tech and a lot of out-of-the-box thinking!
We're also trying to remove human bias and guesswork from the scientific process, as much of the manual lab work we do relies on intuition and hunches built up through years of training and practice in the lab. We're looking to interrogate that knowledge, validate it, and embed it into automated systems so that every process can make the most of the years of experience of our team, as well as the rigour and repeatability of automation.
LabGenius aims to bring together the best of synthetic biology and software engineering to create something new.
As a result, we need to collaborate both within the tech team as well as with our scientists – you can’t automate something you don’t understand! We designed our office with this collaboration in mind. Not only do we all sit together in the same shared space (science and tech team members are intermingled), but our protein-engineering laboratory is built into our office. This not only makes it easy to dive in and out of the lab, but it constantly opens up opportunities for collaboration and encourages knowledge sharing.
Many aspects of our day-to-day work require working really closely with the science team, whether that's optimising an experimental protocol, automating a liquid-handling procedure, or analysing the results of a DNA-sequencing run.
We are also big fans of knowledge sharing, and have a weekly tech-talk slot for someone on either the science or tech side to discuss some of their work, pitched at a general audience. This is both a great way for us all to gain knowledge in new areas, as well as to gain fresh appreciation for the work we all do each day.
Bonded by Love for Product
All of us are here because it's a chance to do something different from the norm.
We love what we do, and are excited to come to work every day. When you have to remind people to go home at the end of the day, you know you have something special! We’re fundamentally changing the way that biology is engineered and producing products that will have a real, positive impact on people’s lives. As far as we’re concerned, it doesn’t get much more inspiring than that!
London is known as the Fintech capital of the world, and has a lot of software startups, but relatively few companies are pushing the boundaries in deep tech and science. We're doing something few other companies in the world are doing, and that motivates us even when we're bogged down in the depths of debugging immensely complex problems.
We're not just taking something off the shelf and putting a new wrapper on it - we're taking a shot at the moon. That's risky, and scary at times, but it's exciting in a way less ambitious projects fail to be.
Our mission requires chaining many complex scientific processes together.
When you do this, errors and issues can easily multiply. We use data to tackle this head-on, by systematically tracking the data from all our automated processes, which helps us remove human bias and guesswork from our work. Why did the latest run of a particular protocol fail? We could either try and guess using scientific intuition and previous experience, or look at the data for that run, and compare and contrast it with previous runs to highlight the key differences in proceedings. Did the temperature change? Was a reagent left out for longer than usual?
This approach also helps to optimise our processes. We want to make our system as efficient as possible, and concentrate effort where it will bring most reward. By systematically tracking every process and every parameter, the answers come straight from the data, avoiding a reliance on guesswork to figure out where to target our efforts.
Data is also key for our evolution engine - it parses vast numbers of DNA sequences to infer rules about how the sequences are constructed, in order to shape our experimental testing. As with many ML systems, the more data it receives, the smarter it gets!
Synthetic biology is all about applying engineering to biology.
Rather than assembling mechanical devices, we’re assembling biological components, and with all the complications that it brings! This means our engineering efforts span software, hardware, and biological systems, all of which have to work together in harmony if we’re to succeed in our goals.
We engineer for a purpose, we automate to free up our science team to work more on the truly cutting-edge parts of our process. We also engineer to standardise, remove bias from the process, and make things more repeatable, testable, and reliable. Our engineering efforts also help to drive the acquisition of data, which as mentioned assists in trying to quantify our processes, as well as to reassess any assumptions we may've made.
Given how we're pushing the boundaries of both the technical and scientific fronts of the business, having a sound engineering approach is key, to avoid losing focus, and to remove error and risk from what we do.
Rapidly Growing Team
LabGenius is growing very rapidly - we've scaled the entire company up from the founding team of 4 up to 22 in the past 12 months, and we're looking to continue that pace going forward!
The software team has also grown a lot. In fact, our team didn't exist before February, and now we're approximately a third of the overall headcount, and hiring fast! In the next 12-18 months, we're hoping to more than double the team again - at that point the software team alone will be bigger than the entire company was at the start of the year.
This rapid growth is tricky, but very necessary given the scope of what we want to achieve. We need people covering everything from hardware all the way up to frontend, and everything in between.
However, we're still a small company, and we're very much interested in finding people who fit rather than filling seats. We'd rather take the time to hire correctly than hire a team of people who aren't passionate and skilled at what they do.
There's always more to do than people to do it, so our responsibilities shift regularly. We can guarantee what you're doing now will not be what you're doing in six months to a year! That means there's a wealth of possibilities to shape your role and your journey, and gain new skills or responsibility. There's also opportunities to shape the team itself, and how we organise ourselves, as well as how we grow.
Wears Many Hats
We're a startup, which means there's always more things to do than people to do them.
In our case, perhaps even more so than a software startup. On just the tech team, we cover hardware integration, automation, high-level integration, optimisation, and AI learning systems, to name just a few. Whilst each of the people on our team has a particular domain of expertise, we all pitch in on whatever is required most urgently, be that hiring, building UIs, devops - you name it!
Actively Practices Inclusion
We really care about building an inclusive environment, and are actively trying to maintain and improve this as we grow our team.
We aim to keep sensible working hours, and support working from home wherever it makes sense. A number of our team members have young families, so we aim to support parents and be family-friendly when planning both office policies as well as team events.
On the recruiting side, we've spent a lot of time trying to eliminate bias in our recruiting process. We run our job adverts through textio, and try to keep our requirements as open as possible to avoid excluding candidates through overly strict requirements (e.g. requiring degrees when work experience can easily be equivalent/superior).