Gen AI - Data Engineer with AWS Experience

Capgemini; Dallas (TX); On-site; USD 51,000 - 81,000; Full time

Benefits offered by this job

Medical

Dental

Vision

Retirement benefits

Job summary

Capgemini is seeking a contract Data Engineer with AWS GenAI expertise to architect and build AI-powered Store AI Agents for store operations. This role blends hands-on engineering with technical leadership, driving GenAI solutions from architecture to production.

You will own end-to-end architecture, design agentic workflows, and optimize RAG solutions while ensuring production readiness and integration with enterprise systems.

Qualifications

• End-to-end LLM, RAG, or agentic AI project delivery.
• Hands-on experience with Generative AI on AWS.
• Experience integrating AI agents with APIs, databases, and enterprise systems.
• Knowledge of Lakehouse/Medallion Architecture and data pipelines.

Responsibilities

• Own end-to-end architecture and implementation of Store AI Agents.
• Design agentic workflows connecting LLMs with APIs, databases, and enterprise systems.
• Build and optimize RAG solutions, including embeddings, vector search, grounding, and context management.
• Define onboarding, testing, deployment, monitoring, and production readiness for new AI agents.
• Set architecture separating LLM reasoning from deterministic backend services.
• Apply Lakehouse/Medallion architecture to AI and data use cases.
• Create scalable approaches for AI/RAG testing, observability, and performance optimization.
• Handle production concerns like latency, context limits, retrieval quality, and reliability.
• Provide technical leadership across AI/ML, data, cloud, application, and business teams.

Skills

LLMs

RAG

AWS GenAI

API integration

Data pipelines

Arch. design

Observability

Security & scalability

Tools

AWS

Vector databases

MCP

Lakehouse

Medallion Architecture

Job description

Capgemini is seeking a contract Data Engineer with AWS experience to architect, build, and scale AI-powered “Store AI Agents” that support store operations. This role blends hands-on engineering with technical leadership, taking GenAI solutions from architecture through production readiness using agentic workflows and RAG capabilities.

Key Responsibilities

• Own end-to-end architecture and implementation of Store AI Agents.
• Design agentic workflows that connect LLMs with APIs, databases, backend services, enterprise applications, and MCP servers.
• Build and optimize RAG solutions, including embeddings, retrieval, vector search, grounding, and context management.
• Define how new AI agents are onboarded and integrated, including testing, deployment, monitoring, and production readiness.
• Set the system architecture that separates LLM reasoning and generation from deterministic backend services.
• Apply Lakehouse/Medallion architecture (Bronze, Silver, Gold) to enable AI and data use cases.
• Create scalable approaches for AI/RAG testing, validation, observability, and performance optimization.
• Handle production engineering concerns such as latency, context limitations, retrieval quality, scalability, and reliability.
• Provide technical leadership across AI/ML, data engineering, cloud, application, and business teams.

Required Qualifications

• Demonstrated experience delivering at least one end-to-end LLM, RAG, or agentic AI project.
• Strong architectural and hands-on experience with Generative AI on AWS.
• Hands-on knowledge of LLMs, RAG, embeddings, vector search, and agentic workflows.
• Experience integrating AI agents with APIs, databases, backend services, and enterprise systems.
• Understanding of MCP (Model Context Protocol) and how agent-to-tool or service integration is implemented.
• Experience with Lakehouse and Medallion Architecture, plus data pipeline optimization.
• Strong grasp of AI testing, observability, security, scalability, latency, and overall production performance.
• Ability to clearly explain end-to-end architecture, technology choices, integration patterns, and design trade-offs.

Technologies

• AWS
• LLMs
• RAG
• Embeddings
• Vector search
• MCP (Model Context Protocol)
• Lakehouse
• Medallion Architecture

Location and Employment Details

• Location: Dallas, TX, United States (onsite)
• Job type: Contract
• Compensation: USD 37 - 59 per hour

Benefits

• Medical
• Dental
• Vision
• Retirement benefits

Preferred

• Experience with AWS-based GenAI and data platforms.
• Experience building enterprise-scale AI agents or multi-agent solutions.
• Exposure to modern vector databases, Lakehouse technologies, and AI orchestration frameworks.
• Strong technical leadership and stakeholder communication skills.