170. Senior Data Engineer (Python, Airflow, AI/LLM)

CrunchCode — міжнародна сервісна ІТ-компанія з досвідом близько 7 років у розробці вебсервісів і вебзастосунків. Ми працюємо у форматах staff augmentation (outstaff) та outsourcing і підключаємо спеціалістів до проєктів клієнтів у довгостроковій моделі співпраці.

Ми працюємо переважно з проєктами в доменах логістики (включно з last mile),e-commerce, fintech та банкінгу, а також enterprise-рішеннями.
Для нас важливо, щоб проєкт був “чистим” і зрозумілим з точки зору етики та цінності для користувачів.

Ми принципово не беремо проєкти, пов’язані з:
● gambling / гемблінгом,
● adult-контентом та порнографією,
● шахрайством або будь-якою розробкою, що спрямована на обман чи маніпуляції.

What We Offer:
● Fully remote work
● Long-term, stable project
● High level of autonomy and trust
● Minimal bureaucracy
● Direct impact on business-critical logistics systems
● Long-term engagement, not a short-term contract.

Project Overview
FinTech data engineering role combining traditional pipeline work with hands-on AI/LLM development. You will design and own data solutions end-to-end — from ETL pipelines and 3rd party integrations to building LLM-powered agents and automation workflows. The role requires product thinking, cross-functional flexibility, and the ability to move from POC to production independently.

Tech Stack: Python · Airflow · dbt · Redshift · AWS · Docker · LangChain · LlamaIndex · LLM APIs · RAG · CI/CD

Requirements (Must-have):
- 4+ years of Data Engineering experience
- Strong end-to-end data engineering background — design and ownership of solutions
- Proficiency in Python, Airflow, dbt, and Redshift
- Experience building and maintaining ETL / ELT pipelines and data integrations
- Hands-on experience with LLM / agent-based automation — building agents or LLM-powered workflows for data transformation, testing, or extraction
- Practical familiarity with LLM APIs (OpenAI, Anthropic, etc.), RAG patterns, prompt engineering, and agent frameworks (LangChain, LlamaIndex, or similar)
- Cross-functional flexibility — Docker, CI/CD, cloud deployment, light backend and frontend for POCs
- Excellent communication skills — able to explain technical decisions to non-technical stakeholders
- Self-directed, proactive, product-thinking mindset

Responsibilities:
- Analyze business workflows and identify opportunities for data and AI-driven automation
- Design, build, and maintain scalable data pipelines and integrations — including ingestion from unreliable or unstructured 3rd party sources
- Build LLM- and agent-based solutions for data transformation, validation, and extraction tasks
- Containerize data and AI workloads using Docker and deploy to AWS
- Develop prototypes and POCs to validate ideas quickly — pipelines and AI-powered workflows
- Collaborate with business and technical teams to refine requirements and iterate on solutions
- Support deployment and integration of data and AI solutions into production
- Contribute to data modeling, quality, and observability practices
- Continuously improve data processes through automation and AI-driven approaches

Nice to Have:
- Experience combining ETL pipelines with LLM/agent components in production or near-production
- Experience with vector stores, embeddings, or RAG
- Familiarity with AWS-based cloud data platforms
- Experience working in cross-functional product teams

Hiring Process: Intro call → Technical discussion → Offer
Duration: Long-term