Meeru AI Inc
Zup Innovation
Senior Data Engineer
PythonSQLAWSTerraform
Automatic translation. Check the original.
About the opportunity
Our purpose is to create technologies that challenge the best in the world and change the game for our clients. Therefore, we seek professionals who want to be part of a culture based on excellence and innovation. If you identify with a collaborative work environment driven by curiosity, come build the future of technology with us.
What you will do here *
- Participate in the process of understanding business needs, understanding and ensuring value delivery; *
- Design the architecture and evaluate available technologies to solve the right problem; *
- Develop and evolve scalable data pipelines prepared to feed Generative AI models and RAG solutions; *
- Implement Data pipelines for data democratization in a Data Mesh architecture, creating semantic layers and structured data for consumption by AI; *
- Combine architecture and technology to develop and deliver reusable components such as connectors, APIs, SDKs, CLIs, integrating with APIs from LLMs (OpenAI, Claude, Gemini); *
- Prototype intelligent agents using frameworks like LangChain, LangGraph, and CrewAI, evaluating cost, latency, and integration quality; *
- Test and automate everything possible; *
- Validate and adapt components according to user feedback; *
- Collaborate with the quality and technological innovation of the product and work environment.
What we expect you to know *
- Knowledge in large-scale data processing, parallel and distributed processing (Apache Spark, Hadoop, Hive, etc); *
- Hands-on experience in ELT using dbt, Data Lake/Lakehouse, and orchestration with Airflow; *
- Experience with cloud data & analytics services from AWS (Glue, EMR, Athena, Quicksight); *
- Knowledge of Python programming language; *
- Proficiency in core AWS Cloud services (S3, Lambda, SQS, DynamoDB, API Gateway); *
- Proficiency in using LLMs, practical application of embeddings, RAG (Retrieval-Augmented Generation), and Vector Databases (Pinecone, Milvus, pgvector, Qdrant, etc.); *
- Skill in Prompt Engineering and orchestration with frameworks like LangChain or LangGraph; *
- Consistent hands-on experience with relational (SQL) and NoSQL (document and key-value) databases; *
- Proficiency in DevOps practices and infrastructure as code (Terraform, CodePipeline, etc).
What would be great if you knew *
- Previous experience in data democratization initiatives with Data Mesh; *
- Experience in benchmarking different market LLMs considering cost-benefit and latency; *
- Experience in generative AI or automation tools applied to data pipelines, such as assisted code generation, automated documentation, or intelligent data quality monitoring; *
- Knowledge of Observability (Cloudwatch, CloudTrail, Prometheus, AppDynamics, Splunk, ElasticSearch, Grafana, etc.); *
- Knowledge of advanced caching techniques for scalable AI systems; *
- Experience in developing solutions for financial institutions.
What we offer you
Here, not only your career matters, we want you to have physical and mental health and well-being for the best professional and personal experience journey of your life.
Career *
- Freedom to work from wherever you want *
- Flexible hours* *
- Education Assistance *
- In-house career development tool *
- Internal guilds and other study and interest groups
Health and well-being *
- Health plan *
- Dental plan *
- Partnership for medication purchases *
- Telemedicine: medical assistance available 24x7 *
- Free online therapy *
- Wellhub *
- Extended maternity leave *
- Extended paternity leave *
- CAZ – Zuppers Assistance Center
Financial comfort *
- Meal and food vouchers *
- Life insurance *
- Transportation voucher *
- Home office assistance *
- Childcare assistance *
- Phone plan assistance *
- Profit and Results Sharing
If you are ready to transform data into strategic decisions and want to be part of an environment that values innovation and growth, come be a zupper! 🚀
