Senior Data Engineer
Position Overview
<\/h2>
Valenta is seeking a highly capable Data Engineer who can\nindependently work on modern data engineering, AI\-driven automation, and client\nsolutions. This is a hands\-on role requiring someone proactive, client\-facing,\nand comfortable working across cloud platforms, APIs, AI/LLM integrations,\nautomation frameworks, and scalable data pipelines.
<\/p>
You'll support active client delivery initiatives involving\nPython development, Azure services, API integrations, LLM\-based fuzzy matching,\nautomation (via Cursor, Claude Code, or similar AI\-assisted development tools),\nand orchestration of complex data workflows.
<\/p>
<\/p>
Key Responsibilities
<\/h2>
\u2022 <\/span><\/span><\/span>Build\nand maintain scalable ETL/ELT pipelines on Azure \u2022 <\/span><\/span><\/span>Develop\nPython\-based automation and data engineering solutions \u2022 <\/span><\/span><\/span>Implement\nLLM\-driven features (fuzzy matching, semantic similarity, prompt engineering) \u2022 <\/span><\/span><\/span>Integrate\nREST APIs and external systems \u2022 <\/span><\/span><\/span>Use\nAI\-assisted development tools (Cursor, Claude Code) for rapid feature\ndevelopment \u2022 <\/span><\/span><\/span>Handle\ndata transformation, validation, cleansing, and optimization \u2022 <\/span><\/span><\/span>Troubleshoot\nproduction issues and optimize pipelines \u2022 <\/span><\/span><\/span>Participate\ndirectly in client discussions and requirement gathering \u2022 <\/span><\/span><\/span>Independently\nmanage assigned deliverables with minimal supervision \u2022 <\/span><\/span><\/span>Strong\nhands\-on Python programming experience \u2022 <\/span><\/span><\/span>Strong\nSQL skills (query optimization, data modeling) \u2022 <\/span><\/span><\/span>Azure\necosystem experience: Azure Data Factory, Azure Functions, Azure SQL, ADLS\nGen2, Azure Storage \u2022 <\/span><\/span><\/span>API\nintegration experience (REST APIs, JSON handling, authentication) \u2022 <\/span><\/span><\/span>ETL/ELT\npipeline architecture and design \u2022 <\/span><\/span><\/span>Git/version\ncontrol \u2022 <\/span><\/span><\/span>Production\nsupport and debugging skills \u2022 <\/span><\/span><\/span>Experience\nwith LLM APIs (OpenAI, Claude, or similar) \u2014 required \u2022 <\/span><\/span><\/span>Understanding\nof embeddings, vector similarity, or semantic matching \u2014 required \u2022 <\/span><\/span><\/span>Exposure\nto prompt engineering or fuzzy matching techniques \u2014 required \u2022 <\/span><\/span><\/span>Experience\nwith AI\-assisted coding tools (Cursor, Claude Code, GitHub Copilot, or similar)\n\u2014 required \u2022 <\/span><\/span><\/span>Understanding\nof automation workflows and integration patterns \u2022 <\/span><\/span><\/span>Excellent\nspoken and written English \u2022 <\/span><\/span><\/span>Comfortable\nspeaking directly with clients and internal stakeholders \u2022 <\/span><\/span><\/span>Strong\nownership mindset \u2022 <\/span><\/span><\/span>Ability\nto work independently and manage timelines under pressure \u2022 <\/span><\/span><\/span>4\u20138\nyears of relevant data engineering experience \u2022 <\/span><\/span><\/span>Prior\nconsulting or client\-facing experience \u2022 <\/span><\/span><\/span>Hands\-on\nexperience in analytics consulting or delivery \u2022 <\/span><\/span><\/span>Production\nexperience in regulated industries (finance, healthcare, etc.) \u2022 <\/span><\/span><\/span>Exposure\nto Power BI, Tableau, or reporting ecosystems
<\/p>
<\/p>
<\/p>
<\/p>
<\/p>
<\/p>
<\/p>
<\/p>
<\/p>
<\/p>Required Technical Skills
<\/h2>Core Data Engineering
<\/h3>
<\/p>
<\/p>
<\/p>
<\/p>
<\/p>
<\/p>
<\/p>
<\/p>AI & LLM Integration (Core Requirement)
<\/h3>
<\/p>
<\/p>
<\/p>
<\/p>
<\/p>
<\/p>Communication & Ownership
<\/h3>
<\/p>
<\/p>
<\/p>
<\/p>
<\/p>Preferred Qualifications
<\/h2>
<\/p>
<\/p>
<\/p>
<\/p>
<\/p>
<\/p>
<\/div><\/span>Requirements<\/h3>
<\/div>
<\/div>
<\/div>
<\/div>
<\/div>
<\/div>
<\/div>
<\/div>
<\/div>
<\/div>
<\/div>
<\/div>
<\/div>
<\/div>
<\/div><\/span>