Applied AI Engineer

Job not on LinkedIn

🔥 0 minutes ago

🇵🇹 Portugal – Remote

⏰ Full Time

🟡 Mid-level

🟠 Senior

🤖 AI Engineer

👻 Ghost score 10%

What it means: how likely this posting is sitting open without active hiring.How to read it: 60% or higher means we think this is a ghost. Lower scores are less of a worry.How we score it: age, reposts, open roles vs team size, how fast jobs close, and whether pay is listed.Fine print: an estimate from public data, not a judgment of the company. Real jobs can score high, so treat it as a hint, not a fact.

Apply Now

Find Similar Remote Jobs

Set Up Email Alert For New Jobs

📊 Check your resume score for this job

Improve your chances of getting an interview by checking your resume score before you apply.

Upload Resume

Block Labs

WebsiteLinkedInAll Job Openings

51 - 200 employees

Founded 2022

💼 Consulting

📣 Marketing

📦 Logistics

Consulting • Marketing • Logistics

Block Labs is a Web3-focused builder, investor, and marketing partner for blockchain projects. The company provides end-to-end blockchain development (smart contracts, decentralized wallets, NFT exchanges, payment gateways), web3-native marketing (social management, influencer/KOL campaigns, paid media, PR, partnerships), and investment support from seed to Series A. Block Labs works with founders to accelerate growth through technical development, go-to-market strategies, and strategic capital, operating from Sofia, Bulgaria.

📋 Description

• Build and own a production Slack-native SQL BI analyst agent that translates natural-language business questions into governed SQL • Validate queries, sanity-check results, and provide cited evidence behind every number • Build executive P&L answers, daily health briefings, and data-backed root cause analyses • Extend agents for customer-facing intent triage, routing, RAG responses, conversational state, localized brand voice, and escalation workflows • Integrate agents with helpdesk and CRM platforms through webhooks, session lifecycle management, intent tagging, and automated escalation tickets • Build risk-stratified tools for back-office APIs with validation, confirmation workflows, and controlled autonomy • Defend agents against prompt injection, tool misuse, and data exfiltration • Build agents using LangGraph, Anthropic Agent SDK, MCP, or equivalent frameworks • Engineer feedback loops, semantic memory, decision audit logging, evaluation harnesses, and regression suites • Build and productionize churn, lifetime value, bonus-sensitivity, player-risk, collusion, bot-play, multi-accounting, and treasury/payment anomaly models • Deploy governed ML signals with versioning, SLAs, freshness, drift, calibration monitoring, and automated retraining • Own multi-vector withdrawal risk scoring and evidence-aware re-scoring • Translate policies into deterministic, configurable, auditable rules; simulate and backtest changes • Design holdouts and control groups, measure uplift, and conduct deep-dive analyses • Build agent supervisor and approval surfaces, review queues, session replay, grading modules, and model/evaluation datasets • Design dashboards for decision audits, agent performance, risk review queues, and KPIs • Report to the Head of Data and coordinate with AI, BI, Infrastructure, Customer Success, and product teams

🎯 Requirements

• 4+ years of experience in software, data science, or machine learning engineering • 1+ years building LLM-powered agents in production • Experience with tool use and function calling, structured outputs, retrieval and memory, and multi-step orchestration • Experience with LangGraph, Anthropic Agent SDK, MCP, or equivalent orchestration frameworks • Production RAG system experience, including grounding, chunking, retrieval quality, hallucination control, and refusal strategies • Knowledge of prompt injection, tool-call abuse, and data leakage defenses • Production ML lifecycle ownership: feature engineering, training, serving, monitoring, and retraining • Experience with fraud, risk, or abuse detection is a strong signal • Statistical rigor in experiment design, holdouts, control groups, uplift measurement, and score calibration • Experience building evaluation harnesses and regression suites for non-deterministic systems • Strong Python • Comfort in TypeScript • Strong SQL skills on columnar analytical databases; ClickHouse preferred • Ability to build stakeholder-ready surfaces using a front-end framework or tools such as Streamlit • Experience designing systems where model outputs feed deterministic execution • Experience with LLM observability and tracing, such as Langfuse or LangSmith • Nice to have: iGaming or high-trust transaction-intensive environments • Nice to have: Helpdesk or CS-platform integration experience • Nice to have: blockchain or crypto-native transaction flows • Nice to have: constrained optimization, bandits, or reinforcement learning • Nice to have: rule engines, decision-management systems, and Slack app development • Nice to have: Kafka or MSK consumers, idempotent processing, and failure handling

🏖️ Benefits

• Fully remote work • Asynchronous-first communication • EU timezone overlap preferred • High autonomy and ownership of domain decisions • Architecture decisions documented and debated • Global, multi-tenant scale engineering environment