How your CV stacks up
Upload your CV to see how well it fits this job role
?%
Senior AI Engineer
Senior AI Engineer
About the Role
Octopus was founded with a mission to use technology to accelerate us towards a low-carbon future. That’s why we created Kraken - our own technology platform from scratch, now serving over 70 million households and making Octopus the number one energy supplier in the UK. We foster a culture by hiring clever, curious, and self-driven people, empowering them with modern tools and infrastructure and granting significant autonomy.
We’ve been utilising Generative AI (GenAI), in real-time, customer-facing environments since 2022—including a system generating tens of thousands of high-quality emails for our Energy Specialists. This platform combines our deep industry knowledge and Octopus communication style with customer-specific data from Kraken.
We are now looking for a Senior AI Engineer. In this role, you’ll build and scale AI systems that enable teams to leverage Generative AI models (LLMs, RAG, Agents). You’ll work directly on pioneering AI projects and the infrastructure that ensures successful GenAI adoption at scale.
Your impact will drive meaningful progress towards Net Zero, within a company deeply committed to transforming energy consumption through innovative technology. You’ll face dynamic challenges, requiring adaptability, rapid prototyping, and the ability to validate approaches quickly.
What You’ll Do
-
Design & Develop AI Platform Services Build reusable, scalable AI services enabling exposure of GenAI models, knowledge retrieval pipelines, and agent workflows to application teams.
-
Knowledge Base Development Build & maintain KBR (Knowledge Base Retrieval) systems to process unstructured documents (PDFs, etc.). Develop embedding pipelines for extracting, chunking, and embedding content.
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.
-
AI Readiness Transform unstructured content into AI-ready data through text cleaning, ambiguity resolution, and machine-readable metadata enrichment.
-
AI Operations (Ops), Evaluation & Observability Establish frameworks for AI output monitoring (relevance, accuracy, safety, drift, cost) and platform observability (latency, cost, usage metrics).
-
Centre of Excellence Serve as the technical AI/LLM knowledge hub for the business, defining best practices and accelerating AI adoption domain-wide.
-
Governance & Guardrails Implement governance layers including PII redaction, input validation, and prompt sanitisation policies.
What You’ll Need
✅ Deep GenAI & RAG Expertise
- 2+ years of hands-on production-ready experience with LLMs.
- Proficient in vector databases (Qdrant, Weaviate, Pinecone, pgVector).
- Experience with or Melissa’s configuration tools (e.g., LangGraph, LlamaIndex).
- Workloads with re-ranking models for improved search accuracy.
- Ability to handle heterogeneous document processing (e.g., PDFs).
✅ Production-Grade Asynchronous Python
- Mastery of AsyncIO, FastAPI, and scalable I/O operations for high-concurrency LLM/data workloads.
- Strong software engineering habits (DRY, unit tests, clean code).
✅ Advanced Context Engineering
- Proven production experience solving RAG challenges:
- Context management.
- Metadata-driven filtering and semantic routing.
- Expand knowledge graph integration (e.g., Neo4j, Яндекс ontology).
✅ Modern Software Practices
- Familiarity with Git workflows, automated testing, and CI/CD pipelines.
- Cloud experience (AWS preferred).
✅ Comfort with Ambiguity
- Willingness to rapidly iterate, prototype/new hypotheses, and implement metrics-driven validation.
Get help with your application
Your very own career expert that helps elevate your application to the next level.
We’d Love if You Had (Bonus Perks)
-
GraphRAG Experience Expertise with knowledge graphs (e.g., Neo4j, JanusGraph) to augment standard vector solutions for highly structured data.
-
Open-Weight Deployments Knowledge of deploying/finetuning open-weight models (e.g., Llama 3, Mistral) using frameworks like vLLM/Ollama. Ability to optimize for **cost/privacy/cost across OpenAI API cost reduction methods.
-
Prompt Caching & Cost Optimisation Hands-on experience implementing semantic caching/cost-control layers to reduce billings.
💚 Why Join Octopus?
Culture & Compensation
- Unpublished salary ranges—we’ll match your experience and negotiate transparently with recruiters
- North star metrics matter more than rigid hierarchies to reflect performance/reward your fit principle** (our "Octo-eness").
- Ranked "Best UK Employer" (Sunday Times 2024).
Accommodations & Flexibility
- Customize your interview experience to meet individual needs—reach out with requirements!
- Equal opportunity employer. No discrimination based on any protected attribute.
Supportive Environment
We use AI tools for initial screening/shortlisting (to avoid hiring bottlenecks) but every hiring decision remains human.
Ask questions via talent@octoenergy.com or connect with our team!
Where to Apply
We’re prototyping a fair system where your identity determines the questions we ask. Send your resume to talent@octoenergy.com—don’t wait for "perfect" alignment! We’re excited to hear from you.
(Our process typically spans ~4 weeks but can adapt to your timing.)
“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