J
Jacobsvia muse
Sr. AI Data Engineer
REMOTEPosted 1w ago
Data EngineerSeniorFull-time#remote
About the Role
Location
Bangalore, All IN Regions, India
Capabilities
Digital and Data
Office Setup
Hybrid
Job ID
\#47952
Industry
Cities \& Places
At Jacobs, we're challenging today to reinvent tomorrow by solving the world's most critical problems for thriving cities, resilient environments, mission\-critical outcomes, operational advancement, scientific discovery and cutting\-edge manufacturing, turning abstract ideas into realities that transform the world for good.
Your impact
* Design and develop data architectures and workflows that support AI and machine learning applications.
* Integrate structured and unstructured data from multiple sources, ensuring information is accessible, traceable, appropriately secured and fit for purpose.
* Build automated ingestion, transformation and processing pipelines using Python, SQL and appropriate cloud data services.
* Develop document\-processing workflows, including extraction, parsing, metadata handling, chunking, validation and preparation for downstream AI applications.
* Implement retrieval\-augmented generation (RAG) workflows, including data preparation, embedding generation, indexing, retrieval and integration with large language model (LLM) services.
* Work with vector search and indexing technologies, including Azure AI Search or equivalent services, where appropriate to the use case.
* Integrate foundation models and managed AI services such as Azure OpenAI or equivalent platforms into application workflows.
* Work with AI engineers, software developers, data scientists, solution architects and subject matter experts to translate business and engineering problems into practical solutions.
* Support evaluation of AI\-enabled workflows through retrieval\-quality checks, output validation, test datasets and repeatable evaluation processes.
* Implement logging, monitoring, error handling, security and performance controls for data and AI workflows.
* Support secure deployment practices, including identity management, secrets management and appropriate network controls.
* Contribute reusable components, technical patterns and reference implementations.
* Troubleshoot and improve deployed workflows, addressing data quality, integration, performance and reliability issues.
* Prepare technical documentation and communicate design decisions, limitations and operational considerations.
Here's what you'll need
* At least 3 years of commercial experience in data engineering, software engineering, AI engineering or a closely related role.
* Strong programming skills in Python and practical experience with SQL.
* Experience building and maintaining ETL/ELT pipelines and integrating data from multiple sources.
* Practical experience with cloud\-based data or application services; Microsoft Azure is preferred.
* Working understanding of machine learning and generative AI concepts, including model inference, embeddings and retrieval.
* Hands\-on experience with RAG or document/knowledge retrieval applications, including some of ingestion, chunking, embedding, indexing or retrieval implementation.
* Experience integrating LLMs or managed AI services through APIs, such as Azure OpenAI or equivalent platforms.
* Understanding of relational databases, data lakes and appropriate data storage patterns.
* Familiarity with API development and integration, testing, Git and collaborative software development practices.
* Understanding of data quality, security, privacy and responsible use of enterprise information.
* Strong analytical and problem\-solving skills and ability to explain technical concepts to stakeholders.
* Good written and spoken English and ability to work effectively with distributed teams.
Nice to have:
* Experience with Azure AI Search, Azure OpenAI, Azure Machine Learning or equivalent AI services.
* Experience with vector databases or vector search technologies, such as PostgreSQL with pgvector, Azure AI Search or equivalent platforms.
* Experience with orchestration frameworks or too
Bangalore, All IN Regions, India
Capabilities
Digital and Data
Office Setup
Hybrid
Job ID
\#47952
Industry
Cities \& Places
At Jacobs, we're challenging today to reinvent tomorrow by solving the world's most critical problems for thriving cities, resilient environments, mission\-critical outcomes, operational advancement, scientific discovery and cutting\-edge manufacturing, turning abstract ideas into realities that transform the world for good.
Your impact
* Design and develop data architectures and workflows that support AI and machine learning applications.
* Integrate structured and unstructured data from multiple sources, ensuring information is accessible, traceable, appropriately secured and fit for purpose.
* Build automated ingestion, transformation and processing pipelines using Python, SQL and appropriate cloud data services.
* Develop document\-processing workflows, including extraction, parsing, metadata handling, chunking, validation and preparation for downstream AI applications.
* Implement retrieval\-augmented generation (RAG) workflows, including data preparation, embedding generation, indexing, retrieval and integration with large language model (LLM) services.
* Work with vector search and indexing technologies, including Azure AI Search or equivalent services, where appropriate to the use case.
* Integrate foundation models and managed AI services such as Azure OpenAI or equivalent platforms into application workflows.
* Work with AI engineers, software developers, data scientists, solution architects and subject matter experts to translate business and engineering problems into practical solutions.
* Support evaluation of AI\-enabled workflows through retrieval\-quality checks, output validation, test datasets and repeatable evaluation processes.
* Implement logging, monitoring, error handling, security and performance controls for data and AI workflows.
* Support secure deployment practices, including identity management, secrets management and appropriate network controls.
* Contribute reusable components, technical patterns and reference implementations.
* Troubleshoot and improve deployed workflows, addressing data quality, integration, performance and reliability issues.
* Prepare technical documentation and communicate design decisions, limitations and operational considerations.
Here's what you'll need
* At least 3 years of commercial experience in data engineering, software engineering, AI engineering or a closely related role.
* Strong programming skills in Python and practical experience with SQL.
* Experience building and maintaining ETL/ELT pipelines and integrating data from multiple sources.
* Practical experience with cloud\-based data or application services; Microsoft Azure is preferred.
* Working understanding of machine learning and generative AI concepts, including model inference, embeddings and retrieval.
* Hands\-on experience with RAG or document/knowledge retrieval applications, including some of ingestion, chunking, embedding, indexing or retrieval implementation.
* Experience integrating LLMs or managed AI services through APIs, such as Azure OpenAI or equivalent platforms.
* Understanding of relational databases, data lakes and appropriate data storage patterns.
* Familiarity with API development and integration, testing, Git and collaborative software development practices.
* Understanding of data quality, security, privacy and responsible use of enterprise information.
* Strong analytical and problem\-solving skills and ability to explain technical concepts to stakeholders.
* Good written and spoken English and ability to work effectively with distributed teams.
Nice to have:
* Experience with Azure AI Search, Azure OpenAI, Azure Machine Learning or equivalent AI services.
* Experience with vector databases or vector search technologies, such as PostgreSQL with pgvector, Azure AI Search or equivalent platforms.
* Experience with orchestration frameworks or too