Senior Data Engineer

About Us
Beamup helps enterprises move beyond dashboards, alerts, and manual triage to automated supply chain execution.
Our AI platform supports large, complex retail and manufacturing networks by deploying specialized AI agents that operate continuously across stores, distribution centers, warehouses, and in-transit operations. These agents detect execution issues, identify root causes, and execute corrective actions - either autonomously or by routing work to the right teams.
Retailers and manufacturers rely on Beamup to replace reactive workflows with consistent, scalable execution — reducing losses, improving performance, and operating with greater confidence at global scale.

Our Mission
To redefine supply chain intelligence by building AI agents that predict, prevent, and resolve inventory health and operational issues in real time.

Job Summary:

As a Senior Data Engineer, you will be helping us design and build a flexible and scalable system that will allow our business to move fast and innovate. You will be expected to show ownership and responsibility for the code you write, but it doesn't stop there. At Beamup, you are encouraged to think big and help out in other areas as well.

Responsibilities:

Designing and writing code that is critical for business growth
Mastering scalability and enterprise-grade SAAS product implementation
Sense of ownership - leading design for new products and initiatives as well as integrating with currently implemented best-practices
Building and owning production-grade ETL/ELT pipelines that power analytics, ML training, and real-time AI systems
Designing data architectures that support agentic systems, including:

Embeddings and vector-based retrieval
RAG pipelines
Feedback loops and continuous improvement
Review your peer's design and code
Work closely with product managers, peer engineers, and business stakeholders

Requirements:

5+ years of hands-on experience as Software Engineer with Strong Python skills (TypeScript / Node.js is a plus)
Hands on experience in managing major clouds vendors' infrastructure (AWS, GCP, Azure)
Proficiency with SQL, modeling and working with relational and non relational databases, and pushing them past their limits
Hands on experience in designing and implementing ML-aware data pipelines (Spark, Airflow), distributed systems and restful APIs
Experience or strong interest in LLMs and agentic systems, including:
Agentic workflows (LangChain, LangGraph)
RAG patterns, Vector databases and embeddings
Evaluating and monitoring AI-driven systems (Langfuse LangSmith)
Familiarity with ML & AI tooling, such as:
Feature stores, training pipelines, or model-serving data flows
ML platforms (MLflow, SageMaker, Vertex, etc.)
Experience with CI/CD, Docker, and Kubernetes
The ability to lead new features from design to implementation, taking into consideration topics such as performance, scalability, and impact on the greater system
Comfortable operating in a fast-moving startup with high ownership and low process
Enjoy communicating and collaborating, sharing your ideas and being open to honest feedback

Beamup is proud to be an equal opportunity employer and provides equal employment opportunities (EEO) to all employees and applicants without regard to race, color, religion, sex, national origin, age, disability, veteran status, sexual orientation, gender identity, or genetics.

You can read more about us at:

https://www.beamup.ai/

And we were also chosen to be one of the 50 most promising Israeli startups of 2023:
https://www.calcalistech.com/ctechnews/article/hjtwkugx2