A complete application in a minute
Tailored resume and cover letter, ready to send.
Capgemini in Princeton, NJ is seeking a Cyber Security Architect for a 3-month on-site contract to design GenAI and agentic architectures on Azure Foundry, with emphasis on security and governance.
You will work on Azure OpenAI, Foundry, MCP, LangGraph, and integrate with enterprise systems, build guardrails for Responsible AI, and ensure regulatory alignment, with 10+ years in software/data/cloud architecture and 3+ years on Azure.
Princeton, NJ, United States (On-site)
Contract (3 months 30 days)
Published 3 days ago
data governance
MLOps/LLMOps
Observability & Monitoring
api management
python programming
Key responsibilities:
Design end to end GenAI and agentic architectures on Azure AI Foundry model selection agents tools retrieval evaluation and deployment
Define multiagent patterns planner executor supervisor handoff human in the loop using Foundry Agent Service Semantic Kernel LangGraph
Architect RAG and knowledge grounding with Azure AI Search vector indexes and Databricks Vector Search over governed data
Integrate agents with enterprise systems through Model Context Protocol MCP Open API tools Azure Functions Logic Apps and API Management
Data and platform:
Connect AI solutions to the lake house Databricks Unity Catalog Delta Lake feature and vector stores and Microsoft Fabric OneLake where present
Shape data products and semantic layers that agents can reliably reason over
Design LLMOps/MLOps pipelines with ML flow Foundry evaluations prompt versioning and CICD in Azure DevOps or GitHub Actions
Responsible AI security and operations:
Build in guardrails Azure AI Content Safety prompt injection defenses PII redaction and grounded answer checks
Apply Entra ID managed identities private networking Key Vault and Defender for Cloud to every design Nice to have
Set up observability tracing cost controls and token budgeting with Azure Monitor and Application Insights
Map solutions to regulatory needs NAIC AI model bulletin NYDFS Part 500 SOC 2 and model risk management Nice to have
Required skills:
What we expect:
Area/Depth
Projects and hubs model catalog Foundry Agent Service prompt flow evaluations tracing content safety
Hands-on production:
Azure OpenAI and models
GPT family and open models function calling structured outputs finetuning basics token and cost management
Agentic AI
Multiagent orchestration tool use memory planning MCP A2A patterns Semantic Kernel AutoGen LangGraph or similar
Hands-on:
RAG and search
Azure AI Search hybrid semantic ranker chunking and embedding strategy retrieval evaluation
AKS Container Apps Functions API Management Event Grid Service Bus Cosmos DB
Security and identity
Entra ID managed identity private endpoints VNet Key Vault RBAC
Architectlevel
Databricks:
Lakehouse on Azure Databricks Unity Catalog Delta Lake MLflow Mosaic AI Vector Search model serving Nice to have
Knowledge some experience on ML-Flow Mosaic nice to have
Python required REST APIs IaC with Bicep or Terraform CICD
Experience and education:
10 years in software data or cloud architecture including 3 years on Azure at architect level
Experience in building Gen AI LLM solutions with at least one agentic system in production or late stage pilot
12 years working with Databricks on Azure
Client facing consulting or solution architecture experience in a services firm or large enterprise
The pay range that the employer in good faith reasonably expects to pay for this position is $37.45/hour - $58.51/hour. Our benefits include medical, dental, vision and retirement benefits. Applications will be accepted on an ongoing basis.
Tundra Technical Solutions is among North America’s leading providers of Staffing and Consulting Services. Our success and our clients’ success are built on a foundation of service excellence. We are an equal opportunity employer, and we do not discriminate on the basis of race, religion, color, national origin, sex, sexual orientation, age, veteran status, disability, genetic information, or other applicable legally protected characteristic. Qualified applicants with arrest or conviction records will be considered for employment in accordance with applicable law, including the Los Angeles County Fair Chance Ordinance for Employers and the California Fair Chance Act. Unincorporated LA County workers: we reasonably believe that criminal history may have a direct, adverse and negative relationship with the following job duties, potentially resulting in the withdrawal of a conditional offer of employment: client provided property, including hardware (both of which may include data) entrusted to you from theft, loss or damage; return all portable client computer hardware in your possession (including the data contained therein) upon completion of the assignment, and; maintain the confidentiality of client proprietary, confidential, or non-public information. In addition, job duties require access to secure and protected client information technology systems and related data security obligations.