Engineering · London# AI Engineer* Full-timeApply for this roleYou will build and scale the AI agents, retrieval, memory and evidence graph behind every Sidney investigation, working directly with the CTO.## About SidneySidney is an AI intelligence platform that runs investigations the way an experienced analyst does. It plans, collects across open, deep and dark sources, grades every source, reasons over the evidence and states plainly what it could not establish, with a human analyst at the decisions that matter.Sidney is live, with a growing base of customer and trial users. Analysts rely on it in their day-to-day work for deep research, person investigations, corporate due diligence and image and video analysis, and what they need shapes what we build next.## What you'll be involved in* Architect and iterate. Work directly with the CTO to turn business objectives into technical reality, on a platform that's already carrying real customer workloads.* Scale what's working. Take core services from “handles our current clients” to “handles an order of magnitude more” without a rewrite. You'll own the calls on data models, concurrency, and cost-per-query that we'll live with for years.* Raise the quality bar. Full-stack ownership across React and Python. Every change ships against live users, so testing, observability, and failure handling aren't a later phase. They're how you build.* Push the AI frontier. Build and refine AI agents, RAG pipelines, memory, and prompt systems that automate genuinely complex intelligence workflows, and make them reliable enough that analysts trust the output on the first read.* Run it in production. Support live deployments, optimise performance, and troubleshoot mission-critical issues in real time. What you build, you operate.* Build the culture. Help define what “excellence” means at Satorus as we scale from founding team to global disruptor.## What we're looking for### The person* Genuinely fascinated by this problem. Intelligence work: what it's for, who relies on it, why manual analysis is a bottleneck worth destroying. You don't need a background in the industry, but you should be the kind of person who reads about it unprompted.* You've taken something past the prototype. Not just “I've built cool stuff”. You've had a system in front of real users, watched it strain, and fixed it properly. You know the difference between a demo and a product because you've made that transition yourself.* Comfortable operating on a moving platform. You can improve architecture, pay down debt, and ship new capability without breaking what clients already rely on. That's a specific skill, and we'd rather hire someone who has it than someone who's only started from scratch.* Strong communicator. You communicate as well as you build. At this size, engineering decisions are business decisions. You can explain a technical trade-off to someone non-technical without dumbing it down, and write things down so they don't have to be re-explained.* Radical candour. We value honesty over politeness. You can challenge an idea and take the challenge back without ego.### Technical skills* Stack. Professional proficiency in React and Python.* Scale and robustness. Demonstrable experience designing systems that handle real production load. You can talk concretely about a bottleneck you found, a failure mode you designed around, or a migration you ran without downtime.* AI focus. Hands-on with agentic AI development, RAG, memory, and prompt engineering, including how you evaluate and monitor these systems, not just build them.* Data and knowledge. Experience modelling data that many pipelines share, and linking records across messy, multi-source data, with provenance on every record.* Core fundamentals. Strong grasp of data structures, algorithms, and system design.* Bonus. Familiarity with AI security; graph data modelling; OSINT data such as corporate registries, sanctions or maritime records; working knowledge of a language other than English, such as Arabic, Chinese or Russian.## What you'll getWe're a small, performance-driven team at one of the fast-growing startups in AI for intelligence work.* Performance-driven, low ego. The best argument wins, not the loudest voice or the longest title. We give direct feedback, expect it back, and hold each other to a high bar.* Ownership from day one. You'll own a real part of Sidney, not a ticket queue. What you decide ships to customers in weeks, not quarters.* Judged on impact. We care about what you ship and what it changes, not hours or visibility. Strong work is noticed quickly and rewarded with more scope and responsibility.* Growth that's real. Sidney is growing fast, and so are the roles inside it. Early hires shape how engineering works here and take on more as we scale.* Work that matters. Your work lands in front of analysts making high-stakes calls, on a product that's already live.## How to applyThe application form takes about twenty minutes. You'll need:* Your CV, as a PDF or Word document.* Links to your LinkedIn, GitHub or something you've shipped, if you have them.* Short written answers to 6 questions about this role, in your own words.No cover letter. A founder reads every application, and we reply to all of them.Apply for this role Back to all rolesLocation: LondonType: Full-timePosted: 1 September 2026Stack: ReactPythonAgentic AIRAGApply for this role Questions before applying? Ask us.Satorus Group builds AI agents for intelligence investigations. Named after *satori*, the Japanese term for a sudden moment of enlightenment. #J-18808-Ljbffr
AI Engineer London ·
