We live in a world that runs on physical industries like energy, logistics, manufacturing. These sectors are essential to our economy and daily lives, yet they are held back by inefficiencies, fragile legacy systems, and decades-old ways of working. This is not just a business problem; it is a societal one. When grids fail, supply chains stall, or factories falter, entire economies are disrupted.

These companies face unique, complex challenges that typical software was never designed to solve. Cogna was founded to change this. Our mission is to give critical industries their own AI-powered Software Factory: a way to build and deploy bespoke digital tools that solve pressing operational challenges.

Since our launch in May 2023, we’ve seen incredible customer traction and revenue growth. We’re backed by leading VCs, including Notion Capital and Hoxton Ventures, and we’re building a world-class team to take on one of the most important challenges of our time.

Tackling challenges at this scale takes people who are curious, adaptable, and motivated by impact. If our mission resonates with you, we encourage you to apply, even if your experience doesn’t match every requirement. We are committed to building a diverse team that reflects the industries and societies we serve.

Overview

We are looking for a creative Software Engineer with a passion for developing scalable, reliable, efficient, and beautiful AI-first software and have a strong sense of ingenuity. You will be part of an all-star early team, building the future of software. We’ve been building product with AI at its core for enterprise customers since the early days of GPT-3.5 to the latest and greatest models, and have built internal tooling to efficiently and effectively work with LLMs. We understand that building reliable products using AI is much more than writing a good prompt. We put a lot of thought and effort into making outputs of LLMs reliable and verifiable in our product, whether that’s code or more unstructured outputs. We have frameworks for evaluation, verification, specialized code and test generation pipelines, agentic behavior, RAG, observability and orchestration tooling, and many more... all widely used across our product, neatly integrated, and informed by real customer and product needs. Each of these are constantly evolving to adapt to the state of the art, and being built by a world-class team who are always experimenting. You’ll be helping to develop these, as well as using them to build the “brain” of our platform: building agents and end-to-end pipelines to understand the customer’s pain points, define requirements, and generate & verify software to address these in a reliable way. We’re truly building at the edge of what’s possible and we need creative minds who can move fast to push the boundaries.

What you’ll do

• Define, build, and maintain reliable AI-first product features, including internal frameworks and tooling for working with LLMs
• Experiment with various AI/LLM techniques, models, and approaches to increase the accuracy and reliability of our outputs.
• Build and improve evaluation systems and benchmarks.
• Design and build reusable application architectures and toolchains, working closely with the software synthesis team.
• Write and ship high-quality, efficient, and reliable code that is extendible, scalable, and observable. You know how to move fast without breaking things and you know how to keep the right balance between experimentation and shipping.
• Take ideas from experimentation to shipping. You intuitively know what a great product looks like.
• Build and help foster an engineering culture that encourages innovation and high-quality code standards, while shipping fast.
• Collaborate closely in a small highly motivated team to build world-class software.

What we’re looking for

• At least 3 years of relevant work experience.
• The drive to work at an early-stage startup. You thrive in a fast-paced, quickly changing, and independent environment.
• You’re highly proficient in modern typed Python, docker, and PostgreSQL.
• Experience in a compiled typed language like Go or Rust, or in modern frontend development is a plus.
• You’re proficient in modern Python ecosystems and toolchains and have worked with them in complex large codebases. You understand the intricacies of them.
• You’re a creative experimentalist at heart and have industry experience in an environment where this was necessary.
• You either have professional experience using LLMs or have enthusiastically experimented in your own time. Industry experience with LLM toolchains and ecosystems (e.g. libraries like Langchain, observability tooling, RAG systems, etc.) is a plus.
• You have a fundamental understanding of code analysis, compilers, domain-specific languages, or related topics, and are keen to learn in this area.
• You are passionate about clean and reusable interfaces, but can iterate fast on them.
• You can work closely with a product manager to turn customer requirements into reliable systems quickly, and iterate from there, while balancing long-term engineering maintenance effort. You’re great at communicating technical systems succinctly to a product-focused audience.
• Familiarity with e2e testing frameworks, large language models, CI/CD tooling, workflow orchestration systems such as Argo or Temporal, and/or experience with Kubernetes is a plus.

Special note about career breaks: We accept candidates with career breaks and CV gaps. Life happens, we get it. Please apply anyway!

What we offer

• Competitive salary and share option plan
• 25 days annual leave, plus public holidays
• Excellent pension scheme, matched to 7.5%
• Private healthcare, including family cover and pre-existing conditions
• Flexible hybrid working with 2 days per fortnight in our Farringdon office, but different
• schedules can be negotiated.
• Regular social events and offsites
• Access to a gym and fitness classes in our office building