Senior Backend Engineer | AI Platform

Plum; Greater London; On-site; GBP 110,000 - 140,000; Full time

Benefits offered by this job

Stock options

Private health insurance

Annual training budget

Remote-friendly with London Athens Cy

Office presence in London

Job summary

Plum is seeking an experienced AI Platform Engineer to build and maintain scalable infrastructure supporting AI-powered products across the company. You’ll own and evolve internal frameworks and services used by multiple product squads.

You will establish best practices for prompt engineering, AI guardrails, and evaluation methodologies, ensuring safe deployment, monitoring, and iteration of AI applications. A strong focus on observability and cost efficiency guides this role.

Qualifications

• 5+ years of experience in Software/Backend/Platform Engineering.
• Experience building backend systems and distributed services in production.
• Experience designing developer platforms and internal tooling for multiple teams.
• Hands-on experience building AI-powered applications using modern LLM frameworks.
• Good understanding of LLMs, Retrieval-Augmented Generation (RAG), Prompt Engineering, AI Guardrails and Evaluation frameworks.
• Experience with AI frameworks such as ADK, LangChain, LangGraph, CrewAI or similar.
• Experience with cloud platforms such as Google Cloud Platform (GCP), AWS, or Azure.
• Strong understanding of observability, monitoring, and incident management.
• Experience with Infrastructure as Code and cloud-native architectures.
• Previous experience in a Platform Engineering team is a plus.

Responsibilities

• Design, build, and maintain a robust, scalable AI Platform supporting AI initiatives across Plum.
• Develop and maintain internal frameworks, libraries, and services used by multiple product squads.
• Promote best practices around prompt engineering, AI guardrails, and evaluation methodologies.
• Build platform capabilities to safely deploy, monitor, and iterate on AI-powered apps.
• Configure and maintain tracing, monitoring, observability, and incident management solutions for platform reliability.
• Collaborate with product and engineering teams to understand needs and provide scalable platform solutions.
• Continuously improve developer experience and platform adoption across the organization.

Skills

Backend Engineering

Distributed Systems

AI Platform

LLM Frameworks

LangChain

ADK

Cloud Platforms

Observability

Incident Management

Infra as Code

Tools

ADK

LangChain

LangGraph

CrewAI

GCP

PostgreSQL

BigQuery

Firestore

Job description

Hey! We’re Plum, your smart saving and investing app on a mission to help grow money for life. Whether you’re stashing the cash for tea and toast in your first home or catching some rays during retirement, Plum’s got your back.

Since 2016, over 2 million people in 10 European markets have set aside more than £2 billion with our clever automation and AI –that’s the magic of Plum! As recognition for our work, we’ve received awards from the likes of Deloitte, Finder, and more.

That’s all down to our passionate team of 200+ Plumsters, who work around Europe to help us achieve our mission. And now we’re looking for more brilliant people to join us on our journey.

The Role

As part of the AI Platform team, you will play a key role in building the foundational infrastructure, frameworks, and tooling that enable AI-powered products and capabilities across the organization. This role requires a high degree of autonomy and ownership, as you'll be responsible for designing scalable solutions that empower multiple engineering teams while ensuring reliability, observability, and cost efficiency.

What are we looking for:

• 5+ years of experience in Software Engineering, Backend Engineering, or Platform Engineering.
• Strong experience building and maintaining backend systems and distributed services in production environments.
• Experience designing developer platforms, internal tooling, shared services, or infrastructure that supports multiple engineering teams.
• Hands-on experience building AI-powered applications and services using modern LLM frameworks and agentic architectures.
• Good understanding of modern AI concepts and practices, including:
• Large Language Models (LLMs)
• Retrieval-Augmented Generation (RAG)
• Prompt Engineering
• AI Guardrails
• AI Evaluation Frameworks
• Experience with AI frameworks such as Agent Development Kit (ADK), LangChain, LangGraph, CrewAI, or similar.
• Experience working with cloud platforms such as Google Cloud Platform (preferred), AWS, or Azure.
• Strong understanding of system reliability, observability, monitoring, and incident management.
• Experience with Infrastructure as Code and cloud-native architectures.
• Previous experience working within a Platform Engineering team is a strong plus.

Key responsibilities:

• Design, build, and maintain a robust, scalable, and cost-effective AI Platform that supports AI initiatives across the organization.
• Develop and maintain internal frameworks, libraries, and services used by multiple product squads.
• Establish and promote best practices around prompt engineering, AI guardrails, and AI evaluation methodologies.
• Build platform capabilities that enable teams to safely deploy, monitor, and iterate on AI-powered applications.
• Configure and maintain tracing, monitoring, observability, and incident management solutions to ensure platform reliability.
• Partner closely with product and engineering teams to understand their needs and provide scalable platform solutions.
• Continuously improve developer experience and platform adoption across the organization.

Tech Stack:

Backend

• Python
• FastAPI
• Agent Development Kit (ADK)

Datastores

• PostgreSQL
• BigQuery
• Firestore

Infrastructure

• Google Cloud Platform (GCP)
• RabbitMQ
• Terraform

Monitoring & Observability

• Grafana
• Prometheus
• Langfuse
• incident.io
• Sentry

What to Expect from Our Hiring Process

At Plum, we value a lot the time you devote to the hiring process, this is why we are always trying to make the process as fast and smooth as possible.

• 30 min. Call with ourTalent Acquisition Team. So we understand better your career plan, tell you more about Plum and the role
• 45 min. Call with our Engineering Lead. Brief technical discussion about the role and your skills
• 120 min. Live Coding Call with our Engineers, including System Design exercise and an Implementation phase
• 30 min. TeamCall with a Product Manager and a Senior Manager from Engineering, for you to understand the business and envision yourself as part of Plum
• Offer

Plum's Perks

• Own part of the company you’re helping grow through stock options
• Private health insurance
• Annual training budget
• Plum Premium for free
• Competitive referral scheme
• Flexible approach to remote working: we encourage at least 2 days a week in one of our beautiful offices in London, Athens or Cyprus
• Team breakfasts and team lunches
• 25 days holiday + bank holidays
• 45 work-from-anywhere days to give you flexibility to work your way
• 2 weeks sabbatical after 4 years to take the break you deserve
• Enhanced parental leave
• 1 paid volunteering day annually
• Annual team trip to a surprise destination!
• A fun, inclusive company culture

If you think this sounds like you, don’t hesitate to get in touch!

Thanks,

Plum Team

*Plum is an Equal Opportunity Employer. Plum does not discriminate on the basis of age, race, religion, sex, gender identity, sexual orientation, non-disqualifying physical or mental disability, national origin or any other basis covered by appropriate law. All employment is decided on the basis of qualifications, merit and business need