Agentic AI · Data Platforms · Berlin

AI agents built for the work beyond the demo.

I am Saurabh Shubham, a Data Engineer building agentic workflows with Claude Code and Pasin. I combine model-driven execution with explicit scope, deterministic checks, and the platform discipline developed across GROPYUS, Sigmoid, and Amdocs.

View resume Email me

Current role: Data Engineer
Location: Berlin, Germany
Experience: 7+ years
Focus: Agentic AI systems

01 / Profile

Reliable AI begins where the model ends.

I focus on the system around the model: context, tool boundaries, orchestration, validation, observability, and human control. Model output is a proposal to verify, not an answer to trust blindly.

My data-engineering background keeps that work grounded. Dependable pipelines, clean interfaces, and reproducible checks are what turn capable models into useful systems.

02 / Applied AI

Bounded autonomy. Visible evidence.

Current practice · Claude Code

AI-assisted engineering workflows

Approach: Use agents across discovery, planning, implementation, testing, and review while keeping task context and acceptance criteria close to the code.
Control: Constrain authority, inspect changes, and require deterministic checks before treating generated work as complete.

Independent workflow · Pasin

Reviewable multi-provider execution

Problem: Long-running agent work needs durable scope, safe execution boundaries, and evidence that survives beyond one conversation.
Design: Planned affected paths, provider routing, sandbox controls, deterministic validation, review gates, and rollback-friendly milestones.
Principle: Agents may make progress autonomously; completion remains an evidence-backed engineering decision.

03 / Engineering foundation

The data systems beneath reliable AI.

Professional experience · GROPYUS

Manufacturing data flows

Problem: Production insight depends on data moving reliably between robotic systems and enterprise platforms.
Contribution: Designed and optimised pipelines and data flows using Python, Dagster, Airflow, dbt, DLT, and Microsoft Azure.
Boundary: Internal topology, production data, and unsupported performance metrics remain private.

Professional experience · Sigmoid

Commercial reporting pipelines

Problem: Commercial reporting required repeatable ETL processing across sales datasets.
Contribution: Built and maintained pipelines using Python, PySpark, Airflow, Pandas, Terraform, Google Cloud, and AWS.
Boundary: Client identity, dataset scale, and business-impact metrics are intentionally omitted.

04 / Experience

From backend integration to data platforms and agents.

2022—Now

GROPYUS
Data Engineer · Berlin
Manufacturing data pipelines and orchestration across Python, Dagster, Airflow, dbt, DLT, and Azure.
2021—2022

Sigmoid
Software Development Engineer · Bengaluru
ETL pipelines for commercial reporting with Python, PySpark, Airflow, Terraform, Google Cloud, and AWS.
2019—2021

Amdocs
Software Engineer · Pune
CRM feature delivery and backend integration using Java, Spring, REST APIs, and SOAP APIs.

05 / Toolkit

Tools in systems context.

Build

Python · SQL · Java · JavaScript

Move and model

Airflow · Dagster · dbt · DLT · PySpark · Pandas

Run

Microsoft Azure · Google Cloud · AWS · Terraform · Git · Unix

Store and connect

PostgreSQL · MySQL · MongoDB · REST · SOAP

Build with AI

Claude Code · Agent orchestration · Context design · Validation gates

06 / Public archive

Earlier hands-on projects.

My public GitHub includes historical JavaScript and Node.js work such as give-me-a-joke and Image-Crawler. These are archived learning projects—not current Data Engineering case studies or production claims.

Browse GitHub profile

Open to relevant conversations

Agentic AI and data-platform work with substance.

Berlin, Germany · relevant European remote markets

saurabh.friday@gmail.com LinkedIn