Octopus Energy Group
Senior AI Engineer
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 serving over 70 million households—making Octopus the number one energy supplier in the UK.
We hire clever, curious, and self-driven people, equipping them with modern tools and infrastructure while empowering autonomy.
Since 2022, we’ve been deploying GenAI in live, customer-facing environments, including a system generating tens of thousands of high-quality emails for our Energy Specialists by combining industry knowledge, brand communication style, and customer-specific Kraken data.
We’re now expanding our GenAI capabilities and seeking a Senior AI Engineer.
In this role, you’ll:
- Build and scale systems using Generative AI models (LLMs, RAG, agents)
- Work closely with cross-functional teams on flagship AI-driven projects
- Solve open-ended problems to accelerate the low-carbon future of energy
- Design scalable solutions while being comfortable with ambiguity and rapid iteration
What You’ll Do
-
Design and Develop AI Platform Services
- Build reusable, scalable services exposing GenAI models, knowledge retrieval pipelines, and agent workflows for application teams.
-
Knowledge Base Development
- Construct and maintain knowledge retrieval systems
- Process heterogeneous documents (PDFs, reports, etc.) and build embedding pipelines for efficient retrieval.
-
AI Readiness & Preprocessing
- Optimize unstructured content for AI systems—clearing ambiguity, refining metadata, and structure for high-quality outputs.
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 Ops, Evaluation & Observability
- Establish frameworks for monitoring:
- Output quality (relevance, accuracy, safety, and drift)
- Platform observability (latency, cost, usage)
- Establish frameworks for monitoring:
-
Centre of Excellence
- Act as the technical AI/GenAI expert for the business, setting best practices and accelerating adoption.
-
Governance & Guardrails
- Implement PII redaction, prompt filtering, and other compliance safeguards in AI systems.
What You’ll Need
-
Deep Generative AI & RAG Expertise
- 2+ years of hands-on experience designing, building, and productionizing LLM applications.
- Expertise in vector databases (e.g., Qdrant, Weaviate, Pinecone, pgvector) and orchestration layers (e.g., LangGraph, LlamaIndex).
- Comfort working with mixed document formats and re-ranking models.
-
Production-Grade Asynchronous Python
- Strong software engineering fundamentals with asyncio and FastAPI skills.
- Experience handling highly concurrent I/O-bound LLM and database calls.
-
Advanced Context Engineering
- Proven experience solving production RAG challenges, including:
- Context window management
- Metadata filtering
- Semantic routing
- Experience with LLM code harnesses (e.g., Claude development harness).
- Proven experience solving production RAG challenges, including:
-
Modern Software Practices
- Git mastery, automated testing, CI/CD
- AWS and cloud platform experience
-
Comfort with Ambiguity & Rapid Learning
- Ability to develop approaches quickly, validate with metrics, and pivot as needed.
Get help with your application
Your very own career expert that helps elevate your application to the next level.
Would Be Great If You Had
- GraphRAG Experience
- Knowledge of Knowledge Graphs (e.g., Neo4j, ontologies) to enhance structured data retrieval.
- Local/Open-Weight Model Deployment
- Experience deploying and fine-tuning open models (Llama 3, Mistral) via vLLM or Ollama for cost and privacy optimisation.
- Prompt Caching & Cost Optimisation
- Techniques for reducing LLM API bills and latency through semantic caching.
Why Join Octopus Energy Group?
✅ Flexible & Fair Salary
- No advertised pay ranges—your exact salary is discussed in the recruitment process.
✅ Exceptional Culture
- Agile, empowering, and fast-moving, bringing new ideas to life.
- Ranked UK’s top employer (Sunday Times, 2024) and top 10 for senior leadership.
- Employee ownership incentivises creativity and growth.
✅ Competitive Perks
- Globe-trotting discounts, fitness memberships, mental health support, and so much more—see our perks hub.
Are You Ready?
- Application Iteration: Our process typically takes 4 weeks, but we remain flexible.
- Accessibility Matters: Let us know about any accommodation needs—we’ll adjust interviews to suit you.
- Equal Opportunity: We strongly encourage applying if you match most criteria—diverse perspectives fuel innovation.
- Commitment to Inclusion: As an equal opportunity employer, we foster fairness and representation.
Ready to become part of Octopus? Reach out at talent@octoenergy.com—or just apply! 🚀
“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