AI Engineer

Role Overview

• Build & Ship AI Systems: Design, develop, and deploy AI-driven automations and multi-agent workflows across group functions including Casino, Sportsbook, Marketing, Operations, and Compliance.
• Integrate hosted AI services (e.g. OpenAI, Anthropic, Google) where the capability genuinely justifies the cost, while prioritising self-hosted open-source alternatives for core operational workflows.
• Deploy, serve, and optimise open-source models (e.g. Llama, Mistral, Qwen, Gemma, Phi families) using frameworks such as vLLM or Ollama, across cloud or on-premise environments.
• Build and maintain retrieval-augmented generation (RAG) pipelines that ground model outputs in company data — including ingestion, chunking, embedding, vector storage, and retrieval quality tuning.
• Develop orchestration and tooling layers (APIs, agent frameworks, function/tool calling, MCP-style integrations) that connect models to internal systems, data sources, and operational workflows.
• Implement evaluation harnesses and benchmarks to compare models against task-specific quality, latency, and cost criteria — feeding results into the team's model selection framework.
• Write production-grade code with appropriate testing, logging, and documentation, following the team's engineering standards for agent design patterns and operational handoff.
• Instrument workflows with monitoring and observability: uptime, latency, token consumption, failure modes, and cost per workflow.
• Harden systems against prompt injection, data leakage, and misuse, and adhere to the group's security, access control, and data governance standards — particularly around sensitive player and operational data.
• Apply cost-reduction techniques in your implementations: model routing between self-hosted and third-party tiers, prompt compression, caching, and batching.
• Track and report the unit economics of the workflows you own, contributing to ROI reporting that links automation output to measurable business outcomes.
• Proactively identify workflows that can be migrated from paid APIs to self-hosted models as open-source capability matures.
• Work directly with stakeholders across the group's companies to understand processes, identify high-value automation opportunities, and translate them into shipped systems.
• Operate with a bias for delivery: prototype fast, validate with real users, iterate, and get working systems into production regularly.
• Document your systems clearly and support smooth operational handoff to the teams that depend on them.
• Contribute to a culture of knowledge sharing within the automation engineering team — code reviews, internal demos, and technical writing.

Requirements

• 3+ years of experience in software engineering, with at least 1 year of hands-on work building LLM-based or AI/ML systems in a production environment.
• Strong programming skills in Python (and ideally TypeScript/JavaScript), including API design and integration work.
• Practical experience working with LLM APIs (OpenAI, Anthropic, Google) and/or deploying open-source models with serving frameworks such as vLLM or Ollama.
• Hands-on experience building RAG pipelines, including embeddings and vector databases (e.g. pgvector, Qdrant, Weaviate, Pinecone, or similar).
• Familiarity with agentic patterns: tool/function calling, multi-step workflows, agent frameworks (e.g. LangGraph, CrewAI, or custom orchestration).
• Solid engineering fundamentals: version control, CI/CD, containerisation (Docker), testing, and observability.
• Comfort working in a fast-moving environment with shifting priorities and a strong output focus.
• Ability to communicate technical concepts clearly to non-technical stakeholders.
• High agency and ownership: you can take a vague problem, scope it, and drive it to a shipped, measured system without waiting to be told each step.
• Comfort with SQL and pulling from data warehouses to feed pipelines and reporting.
• Fluency with AI-assisted engineering workflows (e.g. Claude Code, Codex, spec-driven development) and using them to ship faster.
• Nice to have: Experience in iGaming, fintech, or another regulated, data-intensive industry.
• Exposure to compliance automation use cases: AML monitoring, responsible gambling tooling, regulatory reporting.
• Experience with GPU infrastructure, model quantisation, or inference optimisation.
• Familiarity with workflow automation platforms (e.g. n8n, Temporal, Airflow) and event-driven architectures.
• Contributions to open-source AI projects or published technical writing on AI systems.

Tech Stack

• Airflow
• Cloud
• Docker
• JavaScript
• Python
• SQL
• TypeScript

Benefits

• Attractive remuneration package.
• Monthly bonus based on performance and deposit conversion.
• Wellness benefit (after probation).
• Optician/Spectacle and Blue Lens Benefit (after probation).
• Health Insurance.
• Breakfast/lunch all week.
• Monthly snacks allowance.
• Training support.
• Refer a friend bonus.
• Modern office facilities.
• Exciting Company Events.
• Relocation package (if applicable).