Applied AI Engineer
New
B
Block LabsWeb3, AI, iGaming
Location: Portugal. Secondary Locations: Albania, Georgia, Greece, Bulgaria, Kosovo, Bosnia and Herzegovina, Armenia, Italy, Spain, Malta, Romania, Ireland, Croatia, Serbia, Montenegro, EU timezone overlap is preferred.Full-TimeSenior
Salary not disclosed
Apply NowOpens the employer's application page
Job Details
- Experience
- 4+ years of experience in software, data science, or machine learning engineering, including 1+ years building LLM-powered agents in production
- Required Skills
- PythonSQLMachine LearningTypeScriptClickhouseData scienceLLM
Requirements
- 4+ years of experience in software, data science, or machine learning engineering.
- 1+ years building LLM-powered agents in production using frameworks like LangGraph or Anthropic Agent SDK.
- Experience shipping production RAG systems with grounding, hallucination control, and retrieval optimization.
- Strong Python skills for production services and comfort with TypeScript.
- Strong SQL skills on columnar analytical databases, with a preference for ClickHouse.
- Ownership of the production ML lifecycle including feature engineering, training, serving, and monitoring.
- Statistical rigour in experiment design, uplift measurement, and score calibration.
- Experience with evaluation discipline for non-deterministic systems, including regression suites.
- Experience defending agents against prompt injection, tool-call abuse, and data leakage.
- Ability to build stakeholder-ready interfaces or dashboards using front-end frameworks or Streamlit.
Responsibilities
- Build and own analyst agents end to end that translate natural-language business questions into governed SQL.
- Develop customer-facing agents with intent triage, RAG, and strict escalation logic integrated with CRM/helpdesk platforms.
- Build the risk-stratified tool layer between agents and back-office APIs to harden against adversarial inputs.
- Productionise models for churn, risk scoring, and fraud detection with automated retraining paths.
- Codify business rules into auditable policies and perform backtesting against historical data.
- Build supervisor surfaces and approval dashboards to expose agent reasoning chains and performance metrics.
View Full Description & ApplyYou'll be redirected to the employer's site
