Senior Data Engineer

Position Overview

Valenta is seeking a highly capable Data Engineer who can independently work on modern data engineering, AI-driven automation, and client solutions. This is a hands-on role requiring someone proactive, client-facing, and comfortable working across cloud platforms, APIs, AI/LLM integrations, automation frameworks, and scalable data pipelines.

You'll support active client delivery initiatives involving Python development, Azure services, API integrations, LLM-based fuzzy matching, automation (via Cursor, Claude Code, or similar AI-assisted development tools), and orchestration of complex data workflows.

Key Responsibilities

•       Build and maintain scalable ETL/ELT pipelines on Azure

•       Develop Python-based automation and data engineering solutions

•       Implement LLM-driven features (fuzzy matching, semantic similarity, prompt engineering)

•       Integrate REST APIs and external systems

•       Use AI-assisted development tools (Cursor, Claude Code) for rapid feature development

•       Handle data transformation, validation, cleansing, and optimization

•       Troubleshoot production issues and optimize pipelines

•       Participate directly in client discussions and requirement gathering

•       Independently manage assigned deliverables with minimal supervision

Required Technical Skills

Core Data Engineering

•       Strong hands-on Python programming experience

•       Strong SQL skills (query optimization, data modeling)

•       Azure ecosystem experience: Azure Data Factory, Azure Functions, Azure SQL, ADLS Gen2, Azure Storage

•       API integration experience (REST APIs, JSON handling, authentication)

•       ETL/ELT pipeline architecture and design

•       Git/version control

•       Production support and debugging skills

AI & LLM Integration (Core Requirement)

•       Experience with LLM APIs (OpenAI, Claude, or similar) — required

•       Understanding of embeddings, vector similarity, or semantic matching — required

•       Exposure to prompt engineering or fuzzy matching techniques — required

•       Experience with AI-assisted coding tools (Cursor, Claude Code, GitHub Copilot, or similar) — required

•       Understanding of automation workflows and integration patterns

Communication & Ownership

•       Excellent spoken and written English

•       Comfortable speaking directly with clients and internal stakeholders

•       Strong ownership mindset

•       Ability to work independently and manage timelines under pressure

Preferred Qualifications

•       4–8 years of relevant data engineering experience

•       Prior consulting or client-facing experience

•       Hands-on experience in analytics consulting or delivery

•       Production experience in regulated industries (finance, healthcare, etc.)

•       Exposure to Power BI, Tableau, or reporting ecosystems

Requirements