Artificial Intelligence Engineer

Title: Senior AI Engineer /Solution Engineer — Supply Chain AI Location: Poland, Remote /hybrid Experience: 8+ years Job Description: Required Qualifications Core Programming & Tooling · Strong programming proficiency in Python, producing production-quality, well-structured code. · Proficient in SQL; experience with large-volume datasets in Spark and/or Snowflake. · Comfortable scripting in Python and Bash for automation and tooling. · Expertise with Git for version control, branching strategies, code review, and pull request workflows. · Familiarity with experiment tracking and model versioning (e.g., MLflow). Snowflake · Data lake vs data warehouse architecture (medallion architecture: bronze/silver/gold) · API integration patterns for ingesting from source systems · Schema evolution and handling semi-structured data · Advanced SQL (window functions, CTEs, recursive queries, semi-structured data with VARIANT/JSON) · Warehouse sizing, scaling, and cost optimization · Data sharing, Time Travel, Zero-Copy Cloning · Snowpipe for streaming/continuous ingestion · Role-based access control (RBAC), security, and data governance · Query performance tuning (clustering keys, micro-partitions, query profiling) · Streams and Tasks for CDC and orchestration · Snowpark (Python/Java integration) is increasingly valuable · Model development (staging/intermediate/mart layers) · Jinja templating, macros, and incremental models · Snapshots for SCD Type 2 · dbt testing (schema tests, dbt-utils) · Version control: Git/GitHub or Azure Repos, branching strategies · Orchestration: Airflow, Azure Data Factory, or Dagster · Data modeling: Dimensional modeling (Kimball), star/snowflake schemas · CI/CD: Automated testing and deployment for dbt models and pipelines Machine Learning & Statistical Modeling · Hands-on experience building and deploying ML on large-scale production datasets. · Regression, classification, clustering, and ensemble methods. · Time series forecasting. · Optimization modeling (linear programming, mixed-integer programming). · Feature engineering, data wrangling, backtesting, and statistical analysis on structured data. · Sound evaluation practice: proper train/validation/test splits, leakage avoidance, and forward/out-of-sample validation. LLM Applications & AI Agents · AI agent development: building agentic frameworks using Azure AI Foundry and Azure model endpoints, including tool-use patterns and multi-step orchestration. · Experience with orchestration frameworks such as LangChain or LlamaIndex. · Prompt engineering and chain-of-thought design for complex, multi-step workflows. · RAG pipeline development: chunking, vector embedding/indexing (Azure AI Search), and response generation using LLM endpoints. · Integrating LLMs and agents with structured data sources (SQL/Snowflake), tools, and external systems/APIs. · Grounding, citation, and evaluation techniques to control hallucination and verify model outputs. Document Processing, OCR & NLP · OCR and document parsing using Azure Document Intelligence / Form Recognizer (or equivalent). · Extracting and structuring information from unstructured and semi-structured documents at scale (PDFs, scans, forms, tables). · Text processing and NLP fundamentals: entity extraction, classification, summarization, and semantic search. · LLM-based extraction, comparison, and term/clause analysis across long documents. · Handling document layout, multi-page context, and noisy/low-quality inputs. Azure, Containers & Compute · Core Azure resources: Azure Machine Learning, Azure AI Studio, Azure OpenAI Service, and Azure storage/compute. · Docker: building, optimizing, and managing container images for ML and AI applications. · Azure Container Apps (ACA): containerized deployment, KEDA-based autoscaling, and replica management. · Azure Container Registry (ACR): image management, automated builds, and vulnerability scanning. · Familiarity with serverless compute such as Azure Functions for targeted tasks. MLOps, CI/CD & Deployment · Hands-on DevOps/MLOps experience in production environments. · CI/CD pipeline design and maintenance for ML and LLM workloads using GitHub Actions or Azure DevOps. · Infrastructure as Code with Terraform or Bicep for reproducible Azure environments. · Managing environment promotion and configuration across dev, staging, and prod. · Azure Machine Learning model lifecycle: model registry, automated retraining pipelines, model versioning, and endpoint management. · Deployment strategies (blue-green, canary), rollback procedures, and automated testing for ML pipelines (integration, load, security). · Deploying and scaling LLM-based applications and agent infrastructure on Azure, with attention to latency, throughput, and cost. Monitoring, Observability & Delivery · Delivering production-ready models and services with proper testing, validation, and monitoring. · Azure Monitor and Application Insights: logging, tracing, custom metrics, and alerting. · Model performance monitoring: data drift detection, prediction quality tracking, and automated alerts. · Basic UI skills (Streamlit or Gradio) for quick prototyping and stakeholder demos. Soft/Leadership Skills (Senior-level expectations ) - Technical roadmap ownership / architecture decisions - Setting engineering standards (code review bar, testing standards) across both DE and DS work - Ability to review code/PRs and mentor junior engineers - Stakeholder communication (translating technical concepts to business users) - Documentation and knowledge-sharing practices - Cost optimization mindset (especially critical in Snowflake/Azure environments) - Cross-functional collaboration with analytics, BI, and data science teams - Incident management and troubleshooting production data issues