IT Solution Expert-Data Pipeline and Retrieval Engineer (AI Capability)

Siemens España; Bengaluru; On-site; INR 3,500,000 - 5,200,000; Full time

Job summary

Siemens Technology and Services Private Limited in India is seeking an IT Solution Expert-Data Pipeline and Retrieval Engineer (AI Capability). You will design, build and operate ETL pipelines that move data into a Neo4j knowledge graph and enable AI assistants to retrieve it efficiently.

This hands-on role emphasizes AI-first development, end-to-end SDLC, and close collaboration with ontology engineers. You’ll work with Python, Cypher, vector search, and Azure tools to deliver scalable data

Qualifications

• 8+ years of relevant hands-on experience.
• Strong hands-on Python and solid data-pipeline/ETL engineering.
• Hands-on experience with retrieval/search — vector and similarity search and embeddings.
• Senior, hands-on, self-driven individual contributor who owns outcomes.

Responsibilities

• Build and operate automated ETL pipelines moving data into Neo4j.
• Transform and enrich extracted data to fit ontology/schema.
• Develop retrieval tooling over the graph and vector stores for multi-hop search.
• Implement incremental loading, change detection, retries, error handling, monitoring and data-quality checks.
• Treat each pipeline as a product through its SDLC from requirements to operation.

Skills

Python programming

ETL engineering

Data pipeline

AI-first mindset

Self-driven IC

Tools

Neo4j

Cypher

Azure

Azure AI Search

LangGraph

MCP

APIs

SAP data connectors

Job description

IT Solution Expert-Data Pipeline and Retrieval Engineer (AI Capability)

527252

03-Nov-2026

Information Technology

Information Technology

Siemens Technology and Services Private Limited

Mid-level Professional

We empower our people to stay resilient and relevant in a constantly changing world. We’re looking for people who are always searching for creative ways to grow and learn. People who want to make a real impact, now and in the future. Does that sound like you? Then it seems like you’d make a great addition to our vibrant international team.

We are looking for:Lead Data Pipeline Engineer Consultant

You build and run the pipelines that move knowledge into our Neo4j knowledge graph and make it retrievable for AI assistants. This is a hands-on engineering role — you implement. You work AI-first: you use AI to build and accelerate the pipelines and tooling, and you evaluate that the results are correct. You partner with the Ontology Engineer, who owns the target schema; you make source data fit that schema and flag back when it does not

You’ll make an impact by:

• Understand heterogeneous source data before implementation — identify semantics, dependencies, quality gaps and the real transformation need, rather than coding against the surface.
• Build and operate automated extract-transform-load (ETL) pipelines that pull structured and unstructured content from source systems (SAP, process and documentation tools, documents) and load it into Neo4j.
• Transform and enrich extracted data to fit the canonical ontology/schema.
• Build generic, reusable retrieval tooling over the graph and vector stores — vector, similarity/cosine, hybrid and multi-hop search — independent of any single use case.
• Implement incremental loading, change detection, retries, error handling, monitoring and data-quality checks so pipelines run without manual babysitting.
• Treat each pipeline as a product through its full SDLC: requirements → design → build → test → operate.
• Use AI first to build, accelerate and evaluate your work, and dig into failures hands-on.

You’re excited to build on your existing expertise, including :

• AI First Mindset: you build solutions with AI rather than handcrafting them, and you can judge whether AI output is correct.
• 8+ years of relevant hands-on experience — a super-senior engineer who can steer this topic in the right direction (depth and delivery matter more than years in any single tool).
• Curiosity and a willingness to understand the problem — someone who digs into the subject matter, not a plain developer who hides behind technical skills.
• Strong hands-on Python and solid data-pipeline / ETL engineering — APIs, incremental loads, error handling, automated testing.
• Hands-on experience with retrieval / search — vector and similarity search, embeddings, and at least one real system you built or operated.
• Senior, hands-on, self-driven individual contributor who implements and owns outcomes.
• Nice to have
  • Graph / vector databases, especially Neo4j & Cypher (load and retrieve). Depth here is a plus, not a gate — curiosity plus an AI mindset.
  • Exposure to SAP data (you will pick up the domain with the team and with AI).
  • Agent frameworks, tool-calling / MCP; Azure; CI/CD.
• Python, Neo4j & Cypher, vector search / embeddings, Azure AI Search, LangGraph, MCP & APIs, Azure; connectors to SAP, Signavio and other content sources.
• How we work
  • AI-first, hands-on, outcome-oriented. We implement — no PowerPoint-only architects. Problem-first and pragmatic: we challenge vague requirements and unnecessary complexity, then build a workable alternative.

Create a better #TomorrowWithUs!

This role is based in Pune/Bangalore, where you’ll get the chance to work with teams impacting entire cities, countries - and the shape of things to come.

We value your unique identity and perspective and are fully committed to providing equitable opportunities and building a workplace that reflects the diversity of society. Come bring your authentic self and create a better tomorrow with us.

We’re Siemens. A collection of over 300,000 minds building the future, one day at a time in over 200 countries. We’re dedicated to equality, and we encourage applications that reflect the diversity of the communities we work in. All employment decisions at Siemens are based on qualifications, merit and business need. Bring your curiosity and creativity and help us shape tomorrow.