ai engineer in iGaming

Block Labs is a technology studio operating across Web3, Artificial Intelligence, and iGaming. It builds high-scale, production-grade platforms, including autonomous multi-agent AI systems, decentralized financial infrastructure, and high-frequency iGaming platforms.

• Build and own analyst agents end to end, including Slack-native agents that translate business questions into governed SQL, answer executive P&L questions, post daily health briefings, and explain metric movements;
• Extend agents into customer-facing workflows with intent triage, RAG responses, conversational state machines, localized brand voice, escalation logic, and helpdesk and CRM integrations;
• Build the risk-stratified tool layer between agents and back-office APIs, including validation, confirmation workflows, autonomous execution controls, and security protections;
• Build agents using LangGraph, the Anthropic Agent SDK, Model Context Protocol, or equivalent orchestration frameworks;
• Engineer feedback loops, decision audit logging, evaluation harnesses, and regression suites;
• Build and productionise churn, lifetime value, bonus-sensitivity, player risk, collusion, bot-play, multi-accounting, and anomaly detection models;
• Ship models as governed signals with versioned contracts, monitoring, and automated retraining paths across real-time, near-real-time, and batch tiers;
• Own multi-vector withdrawal risk scoring with cited rationale, confidence, evidence-aware aggregation, and automatic re-scoring;
• Codify business rules with domain owners, simulate and backtest changes, design holdouts and control groups, and run deep-dive analyses;
• Build supervisor and approval surfaces, review queues, session replay, and structured grading modules;
• Design and ship decision audit views, agent performance dashboards, risk review queues, and KPI views;
• Participate in design reviews and own domain decisions.

• 4+ Years of experience in software, data science, or machine learning engineering;
• 1+ Year building LLM-powered agents in production;
• Experience with tool use, function calling, structured outputs, retrieval, memory, and multi-step orchestration;
• Experience shipping a production RAG system and controlling grounding, retrieval quality, hallucinations, and refusal behavior;
• Ability to defend customer-facing agents against prompt injection, tool-call abuse, and data leakage;
• Production ML lifecycle ownership across feature engineering, training, serving, monitoring, and retraining;
• Statistical rigour in experiment design, holdouts, control groups, uplift measurement, and score calibration;
• Experience building evaluation harnesses and regression suites for non-deterministic systems;
• Strong Python, TypeScript proficiency, and strong SQL skills on columnar analytical databases;
• Ability to deliver stakeholder-ready review queues, approval interfaces, dashboards, and lightweight internal apps;
• Experience designing systems where model outputs feed deterministic execution;
• Experience with LLM observability and tracing, plus ownership of shipped systems;
• Nice to have: iGaming or high-trust transaction-intensive environments, helpdesk or CS-platform integrations, blockchain or crypto-native transaction flows, constrained optimisation, bandits or reinforcement learning, rule engines or decision-management systems, Slack app development, Kafka or MSK consumers, idempotent processing, and failure handling.

• Fully remote with asynchronous-first communication;
• EU timezone overlap is preferred;
• Small, high-autonomy Intelligence team within the Data function;
• Reporting to the Head of Data and coordination with AI, BI, Infrastructure, CS, and product teams;
• Architecture decisions are documented and debated;
• Models and agents start in propose-only, human-gated mode and graduate based on simulation and outcome data;
• Multi-tenant scale is required from day one.