Qualification
Experience
10–15 years overall, with strong hands-on background in Data Engineering and AWS
Role Overview
Client is evolving its data platform to enable
Agentic AI and Generative AI–driven workflows
on AWS. We are looking for an Architect who can
initiate and shape this journey
, working closely with existing Data Engineering and ML teams.This role is
not
a pure research or chatbot role. The focus is on
architecting scalable, production-grade GenAI systems
that leverage Deluxe’s existing AWS data ecosystem.The ideal candidate is a strong Data / Cloud Architect who has
upskilled into Generative AI
and understands how to operationalize LLMs, agents, and orchestration patterns in real enterprise environments.
Required Skills & Experience
Core Strengths (Must-Have)
- Strong background in Data Engineering and Cloud Architecture.
- Deep experience with AWS services including S3, Glue, EMR, Redshift, Lambda.
- Hands-on experience with PySpark and large-scale data processing.
- Experience designing and running production data pipelines.
- Solid understanding of distributed systems, scalability, and performance.
Generative AI / Agentic AI (Enablement-Level, Not Research)
- Practical exposure to Generative AI and LLM-based systems.
- Experience implementing:
- Prompt engineering
- RAG pipelines
- Tool/function calling
- Agent orchestration concepts
- Familiarity with GenAI frameworks (LangChain or equivalent).
- Understanding of how to operationalize LLMs in enterprise settings.
Good to Have
- Experience with vector databases (OpenSearch, Pinecone, FAISS, etc.).
- Exposure to MLOps / LLMOps concepts.
- Experience designing APIs and event-driven architectures.
- Prior experience in architect or tech-lead roles.
Key Responsibilities
Agentic AI & GenAI Architecture
- Design end-to-end Agentic AI architectures leveraging LLMs, tools, memory, and orchestration frameworks.
- Define patterns for multi-agent workflows, task decomposition, tool calling, and decision loops.
- Translate business use cases into practical GenAI solutions, beyond basic chatbots.
Cloud & Data Platform Integration
- Architect GenAI solutions that integrate with existing AWS data platforms (S3, Glue, EMR, Redshift, Lambda).
- Design data pipelines to support RAG (Retrieval Augmented Generation) using structured and unstructured data.
- Ensure scalable, secure, and cost-efficient deployments on AWS.
Technology Enablement
- Evaluate and select GenAI frameworks and tools such as:
- LangChain / LangGraph / similar orchestration frameworks
- Vector databases and embeddings
- Model hosting options (managed services, APIs, fine-tuned models)
- Work with Data Engineers and ML teams to define reference architectures and best practices.
Governance, Security & Reliability
- Define guardrails for:
- Data privacy and security
- Prompt/version management
- Observability, monitoring, and cost controls
- Ensure enterprise readiness, not just PoCs.
Collaboration & Mentorship
- Partner with Data Engineering teams to upskill them on GenAI patterns.
- Collaborate with ML teams handling traditional ML and chatbot solutions.
- Act as the technical thought leader for Agentic AI initiatives.
Role
Key Responsibilities
Agentic AI & GenAI Architecture
- Design end-to-end Agentic AI architectures leveraging LLMs, tools, memory, and orchestration frameworks.
- Define patterns for multi-agent workflows, task decomposition, tool calling, and decision loops.
- Translate business use cases into practical GenAI solutions, beyond basic chatbots.
Cloud & Data Platform Integration
- Architect GenAI solutions that integrate with existing AWS data platforms (S3, Glue, EMR, Redshift, Lambda).
- Design data pipelines to support RAG (Retrieval Augmented Generation) using structured and unstructured data.
- Ensure scalable, secure, and cost-efficient deployments on AWS.
Technology Enablement
- Evaluate and select GenAI frameworks and tools such as:
- LangChain / LangGraph / similar orchestration frameworks
- Vector databases and embeddings
- Model hosting options (managed services, APIs, fine-tuned models)
- Work with Data Engineers and ML teams to define reference architectures and best practices.
Governance, Security & Reliability
- Define guardrails for:
- Data privacy and security
- Prompt/version management
- Observability, monitoring, and cost controls
- Ensure enterprise readiness, not just PoCs.
Collaboration & Mentorship
- Partner with Data Engineering teams to upskill them on GenAI patterns.
- Collaborate with ML teams handling traditional ML and chatbot solutions.
- Act as the technical thought leader for Agentic AI initiatives.
Experience
10 to 17 years
Job Reference Number
13029
