Capgemini - Data Engineer - Generative AI/LLM Pipelines
Skills
About the role
This is a data engineering role across Pune, Chennai and Bangalore focused on building pipelines for generative AI and LLM workloads. It suits a data engineer who wants to work on vector storage, RAG systems and AI agent data infrastructure. The employer is Capgemini Technology Services. You'd build ingestion pipelines, manage vector databases and ensure data governance before data reaches AI models.
What you’ll do
- Build ingestion pipelines for unstructured documents, text and media
- Optimize chunking and embedding workflows
- Deploy and manage vector databases such as Pinecone, Qdrant, Weaviate or pgvector
- Engineer context-retrieval pipelines and APIs for RAG systems
- Support model fine-tuning datasets and AI agent workflows
- Design batch pipelines with dbt and Airflow and streaming pipelines with Kafka and Spark
- Build on cloud lakehouses such as Databricks and Snowflake
- Ensure PII masking, data lineage and security compliance
What they’re looking for
- 5+ years in data engineering with hands-on GenAI/LLM pipeline or NLP experience
- Expert Python and SQL skills
- Experience with vector databases and AI orchestration frameworks like LlamaIndex or LangChain
- Proficiency with cloud lakehouses such as Databricks, Snowflake or BigQuery
- Experience with dbt and Airflow orchestration
- Strong knowledge of Git, Docker and CI/CD
Questions about this role
How many years of experience do I need?
5 or more years in data engineering with GenAI/LLM pipeline experience.
What tools does the role use?
Python, SQL, Pinecone/Qdrant/Weaviate/pgvector, dbt, Airflow, Kafka, Spark, Databricks and Snowflake.
Where is this role based?
Pune, Chennai or Bangalore.
Related roles
Capgemini - Lead Data Scientist - Artificial Intelligence Solutions
A senior data scientist role at Capgemini building AI-driven supply chain and manufacturing analytics for enterprise clients. Suited to a candidate with 6-8 years of data science experience and hands-on Python/cloud skills.
Capgemini - Lead - Data Scientist
A lead data scientist role at Capgemini Technology Services focused on manufacturing and supply chain analytics, based across Gurgaon, Chennai or Bangalore. Suits someone with 6-11 years of data science experience who can deliver AI solutions independently and support client-facing work.
Capgemini - MLOps Engineer
An MLOps engineering role across Hyderabad, Pune or Bangalore building and operating multi-cloud ML and LLM infrastructure.
Data Scientist — LLM/VLM
Capgemini is hiring a mid-level Data Scientist in Bangalore for hybrid LLM and VLM project work. The role requires three to seven years of experience plus Python, PyTorch, computer vision and relevant LLM/VLM framework experience.
Python With Gen AI Developer
Python Generative AI Developer role with remote work listed among the available arrangements. The position focuses on Python applications, model deployment, data preparation, and AI solution delivery.
Python GenAI Engineer
A mid-level Python GenAI engineering role at Capgemini in Bengaluru, working hybrid on RAG pipelines and generative AI applications.