Nyxium
Software Engineer
Get notified of more jobs like this · No spam, ever
How your CV stacks up
Upload your CV to see how well it fits this job role
?%
ABOUT NYXIUM
Nyxium turns fragmented, consultant-led infrastructure diligence into a single decision-ready system. When someone is trying to site a data centre, BESS project, or energy asset, the real question is deceptively hard: can this exact plot of land get power, planning permission, and a grid connection, in a timeframe that makes the project viable. Today that gets answered by consultants stitching together PDFs, spreadsheets, GIS layers, and phone calls. We are building the platform that answers it directly, with full source traceability behind every conclusion.
We are early-stage, venture-backed, with a live pipeline and a major launch ahead.
THE PROBLEM YOU WOULD BE WORKING ON
Grid, land, planning, and environmental data are messy, inconsistent, and often contradictory across sources, and none of it was built to be machine-readable. Our agents have to pull from these sources, reason over conflicting or incomplete evidence, and produce an output a developer or investor can act on and trace back to source.
Reasons to use Rodeo
Start with a chat, not a search bar
Grad scheme, placement, apprenticeship? Not sure what you want yet — that's fine. Your agent talks it through with you and turns "I have no idea" into a shortlist.
It searches the market for you
Every day your agent scans the market matching roles against what actually matters to you, not just keywords on a CV.
Only hits
No noise. No "maybe this fits." Just roles with a clear explanation of why they're right — and where to focus when applying.
That is a hard agent design problem. How do you get an LLM-based system to know when it does not have enough evidence, surface uncertainty instead of hallucinating a clean answer, and keep a full provenance trail from raw data to final recommendation. You would work directly on that, building the core reasoning and evidence layer of the product rather than bolting AI onto an existing workflow.
WHAT YOU WOULD DO
- Design and tune agents that pull structured and unstructured data and reason over it reliably
- Build the evidence and confidence layer that lets every output trace back to its source, core to the product rather than a nice-to-have
- Work at the boundary between clean software engineering and genuinely uncertain, adversarial real-world data
- Write TypeScript day to day, bring in Python where it is the better tool, and build it all on Google Cloud
- Shape technical architecture alongside our CTO, with real influence at this stage rather than a token say
Get help with your application
Your very own career expert that helps elevate your application to the next level.
WHAT WE ARE LOOKING FOR
- A senior engineer with strong fundamentals: clean, secure, maintainable production code, not prototypes
- Real experience with LLM agents in production, including where they fail and how you have handled it, hallucination, inconsistent output, unreliable tool calls
- TypeScript day to day, comfortable in cloud-native environments, ideally GCP
- Track record of taking things end to end, and comfortable working with minimal oversight
- Based in or willing to relocate to London
WHERE IT GETS INTERESTING
You do not need all of these, but depth in one or two would matter a lot here:
- Probabilistic graphical models, Bayesian networks, or decision theory. We deal with uncertainty and conflicting evidence constantly, so this sits close to the actual problem
- Knowledge graphs or ontologies, for structuring fragmented data
- Constraint-solving or optimisation
- Explainable AI, where provenance matters as much as the output
- Rules engines or event-driven systems
“It took my CV and asked me questions relevant to understanding what kind of jobs to suggest for me. Suggestions were almost perfect. Jobs were exactly what I’ve been looking for.”
Jessica, London
Skills
Location