AI Engineer

Parkside; Greater London; On-site; GBP 90,000 - 150,000; Full time

Benefits offered by this job

Pension

Employee assistance programme

Learning and development support

Hybrid working

Office in Central London

Job summary

Parkside in London is seeking experienced AI engineers to own and ship production-grade LLM apps, including agent workflows, RAG pipelines and tool integrations. You will partner with product, compliance and operations to deliver safe, scalable AI solutions for real customers and money at scale.

Ideal candidates combine strong software fundamentals with hands-on experience building LLM systems, evaluation, observability, and cloud delivery.

Qualifications

• Strong Python (or TypeScript) and solid software engineering fundamentals.

Responsibilities

• Build and deploy production AI applications using LLMs, including agent workflows, tool use and RAG pipelines over company data.
• Contribute to evaluation frameworks covering accuracy, latency, cost and reliability in a regulated context.
• Implement retrieval systems from ingestion to vector stores and retrieval optimisation.
• Ship production-grade code with observability, error handling, testing and CI/CD.
• Help design guardrails and failure handling for safe AI with real customers and real money.
• At senior levels, lead model/framework choices, mentor engineers and shape AI strategy.

Skills

Python

TypeScript

LLM apps

RAG architectures

Agent frameworks

Observability

Cloud platforms

Tools

LangGraph

Claude Agent SDK

OpenAI SDK

Vector databases

LangSmith

Langfuse

W&B

Job description

About the Company

Our client is a NYSE-listed digital gaming group behind some of the world's best-known sports betting and iGaming brands. Operating across more than 20 countries with close to 3,000 employees, they are one of the largest online gaming businesses in the world, and they are investing seriously in AI across the group.

Betting is a real-time, data-heavy business, and they are putting AI to work across the parts of it that matter most: how customers experience the product, how they keep customers safe, and how the business runs day to day.

The Role

• Customer support automation: LLM agents that resolve account, payment and betting queries end to end, with clean handoff to human agents where it counts
• Safer gambling: systems that help spot at-risk behaviour early and deliver the right intervention at the right moment, built to satisfy regulator scrutiny
• KYC, AML and compliance workflows: document understanding and case summarisation that cut manual review time without cutting corners
• Personalisation: relevant content, offers and CRM messaging generated and tested at scale
• Internal tooling: copilots that give trading, CS and compliance teams faster answers from the company's own data

These are applied LLM engineering roles, not quant or pricing roles. You will work closely with senior stakeholders across product, compliance and operations, and own what you ship.

What You'll Do

• Build and deploy production AI applications using LLMs, including agent workflows, tool use and RAG pipelines over company data
• Contribute to evaluation frameworks covering accuracy, latency, cost and reliability, with the extra rigour a regulated industry demands
• Implement retrieval systems from ingestion and chunking through to vector stores and retrieval optimisation
• Ship production-grade code with proper observability, error handling, testing and CI/CD
• Help design guardrails and failure handling so AI systems behave safely with real customers and real money involved
• At senior levels, lead model and framework choices, mentor other engineers and shape how the group builds with AI

What You'll Need

• Strong Python (or TypeScript) and solid software engineering fundamentals
• Hands‑on experience building LLM applications or agents, whether in production, at work or through substantial personal projects, with a genuine understanding of their capabilities, limitations and failure modes
• Practical familiarity with RAG architectures, vector databases and prompt engineering
• Exposure to agent frameworks (LangGraph, Claude Agent SDK, OpenAI SDK) or equivalent custom implementations
• An interest in LLM evaluation, debugging and observability
• Cloud platform experience (AWS, GCP or Azure) is a plus at junior level and expected at senior level

The bar scales with the level. For senior roles we will expect production LLM systems shipped and owned end to end. For earlier-career roles we care most about strong engineering fundamentals and real, demonstrable work with LLMs.

Nice to Have

• Experience in a regulated industry (gambling, financial services, insurance) and familiarity with responsible AI, auditability and governance
• Experience with high‑traffic, real‑time consumer platforms
• Fine‑tuning experience and the judgement to know when it beats prompting or RAG
• Observability tooling (LangSmith, Langfuse, W&B) and cost optimisation
• Experience with AI coding tools (Claude Code, Codex, Copilot)

What's on Offer

• Competitive salary benchmarked to your level and experience, plus discretionary bonus
• Pension, employee assistance programme and strong learning and development support
• Genuine production scale: millions of customers, live products, measurable outcomes
• The chance to shape how one of the biggest names in the industry uses AI
• Central London office with hybrid working