Hands-On Big Data Architect - Hybrid Chicago
Publicis Sapient · Arlington, VA · 2 days ago
$135k–$190k/yrFull-time
We need to output HTML fragment with sections: About the role? The job description includes paragraphs. We need headings for sections like About the role, Responsibilities, Requirements, Qualifications, Skills, Benefits, Pay, Schedule. Only include sections if posting has real specific content.
We have content: Job Description Manager Big Data Engineering - Hybrid Chicago. Then description paragraphs: "As a Manager Data Engineering, you will be responsible for designing, building, and optimizing data platforms..." etc. That's responsibilities. Then "Your Impact:" bullet-like sentences. Then "Qualifications" heading present in posting. Then "Your Skills & Experience:" then list of qualifications. Then "AI Engineering & Modern Data Platform Experience:" more qualifications. Then "Set Yourself Apart With:" more qualifications. Then "Additional Information" includes Salary Range, inclusive workplace, benefits etc. Also "Company Description". We need to remove boilerplate like EEO etc. Also remove application instructions (none). Remove duplicated lines.
We need to produce sections: maybe About the role (intro paragraph), Responsibilities (the bullet-like responsibilities), Requirements/Qualifications (combined?), Skills (maybe separate), Benefits, Pay, Schedule. The posting includes Salary Range and benefits description. No explicit schedule (hybrid Chicago indicates hybrid work). That could be schedule? It says Hybrid Chicago. That's location/hybrid schedule. Could treat as Schedule? Probably we can include Schedule section with "Hybrid work arrangement in Chicago". But we need to ensure we only include if posting has real specific content. It says Hybrid Chicago, which indicates hybrid work. That's schedule info. So we can include Schedule.
Benefits: posting mentions "Competitive compensation and benefits package.Flexibility to support work-life balance.Comprehensive health benefits for you and your family.Generous paid leave and holidays.Wellness program and employee assistance." That's benefits.
Pay: Salary Range: $135,000 - $190,000.
Thus we will have sections: About the role (intro), Responsibilities (the bullet list after "Your Impact:" maybe also earlier responsibilities), Qualifications (maybe combine Skills & Experience, AI Engineering..., Set Yourself Apart With). Could also split Skills and Qualifications but we can combine into Qualifications. The instruction: use headings for section headings (e.g. About the role, Responsibilities, Requirements, Qualifications, Skills, Benefits, Pay, Schedule). We can choose which to include. Probably include About the role, Responsibilities, Qualifications, Benefits, Pay, Schedule. Not Requirements separate if covered.
We need to use for each section heading. Use
for each section heading. Use - for any list of duties/requirements/benefits. Use
for prose.
We must preserve ALL substantive information; do not invent or summarize away detail. So we need to keep all details from the posting, but we can format as lists.
We need to extract the responsibilities list: The "Your Impact:" sentences each start with a verb. They are:
- Combine your technical expertise and problem-solving passion to work closely with clients, turning complex ideas into end-to-end data solutions that transform our clients’ business.
- Translate client requirements into system design and develop solutions that deliver measurable business value.
- Lead, design, develop and deliver large-scale data systems, data processing, data transformation, and data platform modernization initiatives.
- Build and optimize batch and streaming data pipelines across modern cloud data platforms and distributed processing frameworks.
- Support AI-enabled engineering use cases by designing high-quality data foundations, retrieval patterns, context engineering approaches, and scalable data services that power agentic and machine learning solutions.
- Automate data platform operations and manage post-production systems, observability, quality, reliability, and operational processes, including telemetry pipelines that capture prompt, response, trace, latency, token, and cost data for AI-enabled services in a queryable form.
- Conduct technical feasibility assessments and provide project estimates for the design and development of solutions.
- Mentor, support, and grow junior team members while contributing hands-on to delivery.
We should keep each as
- .
Then the "Qualifications" section includes many bullet-like items under "Your Skills & Experience:" and then "AI Engineering & Modern Data Platform Experience:" and "Set Yourself Apart With:".
We need to preserve all details. We'll create a
with all qualification items.
Let's list them:
From "Your Skills & Experience:":
- Demonstrable experience implementing end-to-end data pipelines and production-grade data platforms.
- Hands-on experience with at least one leading public cloud data platform: Amazon Web Services, Microsoft Azure, or Google Cloud Platform;
- Experience with Databricks as a data engineering platform is strongly preferred, including working with notebooks, jobs, Delta Lake, or similar lakehouse patterns.
- Strong Python proficiency and practical experience using Python-based tooling for data engineering, automation, platform development, or AI engineering workflows.
- Implementation experience with column-oriented database technologies such as BigQuery, Redshift, Vertica, or similar platforms; NoSQL database technologies such as DynamoDB, Bigtable, Cosmos DB, or similar; and traditional database systems such as SQL Server, Oracle, or MySQL.
- Experience implementing data pipelines for both streaming and batch integrations using tools and frameworks such as Glue ETL, Lambda, Google Cloud Dataflow, Azure Data Factory, Spark, Spark Streaming, or similar technologies.
- Experience with data modeling, warehouse design, fact/dimension implementations, and modern lakehouse or data mesh patterns.
- Experience with code repositories, continuous integration, automated testing, release management, and production support practices.
- Familiarity with MLOps concepts and the data engineering responsibilities required to support AI/ML deployment, validation, monitoring, rollback, and operational reliability.
- Ability to handle module or track-level responsibilities while contributing to tasks hands-on.
- Good communication skills and willingness to work as part of a collaborative, cross-functional team.
From "AI Engineering & Modern Data Platform Experience:":
- Exposure to AI engineering patterns, including context engineering, retrieval-augmented generation support patterns, agent architectures, and production data services that support AI-enabled experiences.
- Experience building and maintaining the pipelines behind retrieval systems, including document parsing, chunking, metadata extraction, embedding generation, and incremental reindexing, alongside the vector databases, graph databases, semantic search, and knowledge retrieval structures they feed.
- Exposure to agentic platforms or cloud AI services such as Vertex AI, Azure AI services, AWS AI services, or comparable platforms; specific platform experience is less important than understanding how AI engineering differs from traditional data engineering.
- Practical experience deploying agents, integrating agent frameworks, or supporting agentic workflows in production or near-production environments is a plus.
- Experience building evaluation data infrastructure for AI systems, including ground-truth and golden datasets, offline evaluation pipelines, and the data scaffolding behind LLM-as-judge and regression testing.
- Experience modeling and persisting agent state, including session context, conversation history, and memory stores, treating them as a durable storage and data modeling problem rather than an application detail.
- Support AI-enabled engineering use cases by designing high-quality data foundations, retrieval patterns, context engineering approaches, and scalable data services that power agentic and machine learning solutions, applying the same lineage, provenance, and data contract rigor to context and retrieval sources that you would to a production warehouse.
- Experience with agentic harnesses or orchestration tools such as Pi, Hermes Agent, or similar platforms is a plus, but not required.
- Experience with Snowflake and zero-copy architecture patterns is a plus, particularly for retail, financial services, energy, or CPG-oriented use cases.
From "Set Yourself Apart With:":
- Developer certifications for AWS, Google Cloud, Microsoft Azure, Databricks, Snowflake, or related cloud/data platforms.
- Demonstrated experience applying AI engineering concepts in practical business environments rather than only academic or research settings.
- Hands-on experience supporting AI/ML and LLM lifecycle needs such as model deployment support, monitoring, validation, shadow deployments, release management, and evaluation or data quality measurement for both predictive models and generative systems.
- Experience in retail, financial services, energy, CPG, logistics, manufacturing, or other data-rich industries where applied AI and large-scale data engineering are used to solve operational or client-facing problems.
- Understanding of Agile, product, and delivery methodologies in consulting or client-facing environments.
Now Benefits: list:
- Competitive compensation and benefits package.
- Flexibility to support work-life balance.
- Comprehensive health benefits for you and your family.
- Generous paid leave and holidays.
- Wellness program and employee assistance.
Pay: Salary Range: $135,000 - $190,000 (note about range may differ). We'll keep that sentence.
Schedule: Hybrid Chicago (Hybrid work arrangement). We'll phrase: Hybrid work arrangement in Chicago.
About the role: The introductory paragraph: "As a Manager Data Engineering, you will be responsible for designing, building, and optimizing data platforms that enable scalable, high-performance data processing and analytics. You will work closely with cross-functional teams to develop and implement data solutions that drive business insights and innovation." That's the first two sentences before "Your Impact:".
We'll put that in .
Now we need to output HTML fragment only, no /. Use
headings.
Structure:
About the role
...
Responsibilities
- ...
...
Qualifications
... all qualification items ...
Benefits
... benefits ...
Pay
Salary Range: $135,000 - $190,000. The range shown represents a grouping of relevant ranges currently in use at Publicis Sapient. Actual range for this position may differ, depending on location and specific skillset required for the work.
Schedule
Hybrid work arrangement in Chicago.
We must ensure we don't repeat job title as heading. We didn't.
We must not include boilerplate like EEO etc. We removed.
Check for duplicated lines: none.
Now ensure we preserve all substantive information: Did we miss any? The "Your Impact:" we turned into responsibilities list. Good.
The "Additional Information" also includes "An inclusive workplace that promotes diversity and collaboration." That's a benefit/diversity statement; we might include under Benefits? It's a statement about inclusive workplace. Could be part of Benefits or maybe we could add a separate section but we only have Benefits heading. We could add that as a bullet under Benefits. It's substantive. Let's add: "An inclusive workplace that promotes diversity and collaboration." Also "Access to ongoing learning and development opportunities." That's also a benefit. We missed those. Also "Competitive compensation and benefits package." we have. Also "Flexibility to support work-life balance." we have. Also "Comprehensive health benefits for you and your family." we have. Also "Generous paid leave and holidays." we have. Also "Wellness program and employee assistance." we have. Also "Access to ongoing learning and development opportunities." add. Also "An inclusive workplace that promotes diversity and collaboration." add.
Thus Benefits list items:
- Competitive compensation and benefits package.
- Flexibility to support work-life balance.
- Comprehensive health benefits for you and your family.
- Generous paid leave and holidays.
- Wellness program and employee assistance.
- Access to ongoing learning and development opportunities.
- An inclusive workplace that promotes diversity and collaboration.
Now check if any other substantive info: "Company Description" paragraph about Publicis Sapient. That's substantive but maybe not required to include? The instruction: Preserve ALL substantive information; do NOT invent or summarize away detail. So we should include company description. Where to put? Could be a section "Company Overview" but not in allowed headings list. However we could include under About the role? Might be okay to add a separate section but headings list is just examples; we can use other headings? The instruction: "Use for section headings (e.g. About the role, Responsibilities, Requirements, Qualifications, Skills, Benefits, Pay, Schedule)." The e.g. suggests those are examples, not exclusive
for prose. We must preserve ALL substantive information; do not invent or summarize away detail. So we need to keep all details from the posting, but we can format as lists. We need to extract the responsibilities list: The "Your Impact:" sentences each start with a verb. They are: - Combine your technical expertise and problem-solving passion to work closely with clients, turning complex ideas into end-to-end data solutions that transform our clients’ business. - Translate client requirements into system design and develop solutions that deliver measurable business value. - Lead, design, develop and deliver large-scale data systems, data processing, data transformation, and data platform modernization initiatives. - Build and optimize batch and streaming data pipelines across modern cloud data platforms and distributed processing frameworks. - Support AI-enabled engineering use cases by designing high-quality data foundations, retrieval patterns, context engineering approaches, and scalable data services that power agentic and machine learning solutions. - Automate data platform operations and manage post-production systems, observability, quality, reliability, and operational processes, including telemetry pipelines that capture prompt, response, trace, latency, token, and cost data for AI-enabled services in a queryable form. - Conduct technical feasibility assessments and provide project estimates for the design and development of solutions. - Mentor, support, and grow junior team members while contributing hands-on to delivery. We should keep each as
- with all qualification items.
Let's list them:
From "Your Skills & Experience:":
- Demonstrable experience implementing end-to-end data pipelines and production-grade data platforms.
- Hands-on experience with at least one leading public cloud data platform: Amazon Web Services, Microsoft Azure, or Google Cloud Platform;
- Experience with Databricks as a data engineering platform is strongly preferred, including working with notebooks, jobs, Delta Lake, or similar lakehouse patterns.
- Strong Python proficiency and practical experience using Python-based tooling for data engineering, automation, platform development, or AI engineering workflows.
- Implementation experience with column-oriented database technologies such as BigQuery, Redshift, Vertica, or similar platforms; NoSQL database technologies such as DynamoDB, Bigtable, Cosmos DB, or similar; and traditional database systems such as SQL Server, Oracle, or MySQL.
- Experience implementing data pipelines for both streaming and batch integrations using tools and frameworks such as Glue ETL, Lambda, Google Cloud Dataflow, Azure Data Factory, Spark, Spark Streaming, or similar technologies.
- Experience with data modeling, warehouse design, fact/dimension implementations, and modern lakehouse or data mesh patterns.
- Experience with code repositories, continuous integration, automated testing, release management, and production support practices.
- Familiarity with MLOps concepts and the data engineering responsibilities required to support AI/ML deployment, validation, monitoring, rollback, and operational reliability.
- Ability to handle module or track-level responsibilities while contributing to tasks hands-on.
- Good communication skills and willingness to work as part of a collaborative, cross-functional team.
From "AI Engineering & Modern Data Platform Experience:":
- Exposure to AI engineering patterns, including context engineering, retrieval-augmented generation support patterns, agent architectures, and production data services that support AI-enabled experiences.
- Experience building and maintaining the pipelines behind retrieval systems, including document parsing, chunking, metadata extraction, embedding generation, and incremental reindexing, alongside the vector databases, graph databases, semantic search, and knowledge retrieval structures they feed.
- Exposure to agentic platforms or cloud AI services such as Vertex AI, Azure AI services, AWS AI services, or comparable platforms; specific platform experience is less important than understanding how AI engineering differs from traditional data engineering.
- Practical experience deploying agents, integrating agent frameworks, or supporting agentic workflows in production or near-production environments is a plus.
- Experience building evaluation data infrastructure for AI systems, including ground-truth and golden datasets, offline evaluation pipelines, and the data scaffolding behind LLM-as-judge and regression testing.
- Experience modeling and persisting agent state, including session context, conversation history, and memory stores, treating them as a durable storage and data modeling problem rather than an application detail.
- Support AI-enabled engineering use cases by designing high-quality data foundations, retrieval patterns, context engineering approaches, and scalable data services that power agentic and machine learning solutions, applying the same lineage, provenance, and data contract rigor to context and retrieval sources that you would to a production warehouse.
- Experience with agentic harnesses or orchestration tools such as Pi, Hermes Agent, or similar platforms is a plus, but not required.
- Experience with Snowflake and zero-copy architecture patterns is a plus, particularly for retail, financial services, energy, or CPG-oriented use cases.
From "Set Yourself Apart With:":
- Developer certifications for AWS, Google Cloud, Microsoft Azure, Databricks, Snowflake, or related cloud/data platforms.
- Demonstrated experience applying AI engineering concepts in practical business environments rather than only academic or research settings.
- Hands-on experience supporting AI/ML and LLM lifecycle needs such as model deployment support, monitoring, validation, shadow deployments, release management, and evaluation or data quality measurement for both predictive models and generative systems.
- Experience in retail, financial services, energy, CPG, logistics, manufacturing, or other data-rich industries where applied AI and large-scale data engineering are used to solve operational or client-facing problems.
- Understanding of Agile, product, and delivery methodologies in consulting or client-facing environments.
Now Benefits: list:
- Competitive compensation and benefits package.
- Flexibility to support work-life balance.
- Comprehensive health benefits for you and your family.
- Generous paid leave and holidays.
- Wellness program and employee assistance.
Pay: Salary Range: $135,000 - $190,000 (note about range may differ). We'll keep that sentence.
Schedule: Hybrid Chicago (Hybrid work arrangement). We'll phrase: Hybrid work arrangement in Chicago.
About the role: The introductory paragraph: "As a Manager Data Engineering, you will be responsible for designing, building, and optimizing data platforms that enable scalable, high-performance data processing and analytics. You will work closely with cross-functional teams to develop and implement data solutions that drive business insights and innovation." That's the first two sentences before "Your Impact:".
We'll put that in
- ... ...
. Now we need to output HTML fragment only, no /. Use
headings.
Structure:
About the role
...
Responsibilities
Qualifications
-
... all qualification items ...
Benefits
-
... benefits ...
Pay
Salary Range: $135,000 - $190,000. The range shown represents a grouping of relevant ranges currently in use at Publicis Sapient. Actual range for this position may differ, depending on location and specific skillset required for the work.
Schedule
Hybrid work arrangement in Chicago.
We must ensure we don't repeat job title as heading. We didn't. We must not include boilerplate like EEO etc. We removed. Check for duplicated lines: none. Now ensure we preserve all substantive information: Did we miss any? The "Your Impact:" we turned into responsibilities list. Good. The "Additional Information" also includes "An inclusive workplace that promotes diversity and collaboration." That's a benefit/diversity statement; we might include under Benefits? It's a statement about inclusive workplace. Could be part of Benefits or maybe we could add a separate section but we only have Benefits heading. We could add that as a bullet under Benefits. It's substantive. Let's add: "An inclusive workplace that promotes diversity and collaboration." Also "Access to ongoing learning and development opportunities." That's also a benefit. We missed those. Also "Competitive compensation and benefits package." we have. Also "Flexibility to support work-life balance." we have. Also "Comprehensive health benefits for you and your family." we have. Also "Generous paid leave and holidays." we have. Also "Wellness program and employee assistance." we have. Also "Access to ongoing learning and development opportunities." add. Also "An inclusive workplace that promotes diversity and collaboration." add. Thus Benefits list items: - Competitive compensation and benefits package. - Flexibility to support work-life balance. - Comprehensive health benefits for you and your family. - Generous paid leave and holidays. - Wellness program and employee assistance. - Access to ongoing learning and development opportunities. - An inclusive workplace that promotes diversity and collaboration. Now check if any other substantive info: "Company Description" paragraph about Publicis Sapient. That's substantive but maybe not required to include? The instruction: Preserve ALL substantive information; do NOT invent or summarize away detail. So we should include company description. Where to put? Could be a section "Company Overview" but not in allowed headings list. However we could include under About the role? Might be okay to add a separate section but headings list is just examples; we can use other headings? The instruction: "Use