AI Engineer
Indexed description
Roles and Responsibilities
- Design, build, and maintain multi-agent AI systems using Agent-to-Agent frameworks, including agent roles, communication contracts, orchestration patterns, and lifecycle management.
- Implement and enhance Model Context Protocol integrations to support standardized context sharing, memory management, and tool access across distributed AI pipelines.
- Develop embedding pipelines, prompt engineering strategies, and context engineering approaches for retrieval-augmented generation and LLM-based applications.
- Build production-grade AI services, ML inference wrappers, APIs, and asynchronous components using Python, Java, and/or Go.
- Deploy and manage scalable AI workloads on Azure using Azure Functions, Azure Container Apps, API Management, Event Grid, Service Bus, and related cloud services.
- Design and optimize data and storage solutions using Azure AI Search, Redis, Cosmos DB, Blob Storage, and related vector or caching technologies.
- Apply cloud-native architecture principles to ensure scalability, resiliency, performance optimization, observability, and cost efficiency across AI platforms.
- Collaborate with engineering, product, data science, and DevOps teams to deliver reliable AI solutions, technical documentation, architecture decisions, and stakeholder updates.
- Hands-on experience with Agentic Layer, Agent-to-Agent frameworks, and Model Context Protocol.
- Strong AI/ML engineering experience, including vector embeddings, prompt engineering, context engineering, and retrieval-augmented generation concepts.
- Strong programming experience in at least two of the following languages: Python, Java, and Go.
- Proven experience deploying cloud-native solutions on Microsoft Azure.
- Experience with Azure AI Search, Redis, Cosmos DB, and related database or vector search technologies.
- Experience designing and managing Azure Functions and Azure Container Apps.
- Strong understanding of cloud-native architecture, scalability, performance optimization, monitoring, and distributed system design.
- Excellent communication skills with the ability to explain complex technical concepts to technical and non-technical stakeholders.
- Experience with Azure Blob Storage and document ingestion pipelines.
- Exposure to Iceberg-based lakehouse patterns for large-scale training data management or offline AI evaluation datasets.
- Experience with emerging agentic frameworks such as LangGraph, AutoGen, CrewAI, or custom multi-agent frameworks.
- Experience with Infrastructure-as-Code tools such as Bicep, Terraform, or ARM templates.
- Experience with distributed tracing, structured logging, metrics dashboards, load testing, and capacity planning.
- Client interview is required before candidate finalization.
- Client interview availability is Monday through Friday, 9:00 AM to 5:00 PM ET/CT/PT.
- Please note: A few of our roles may require in-person interviews at Cognizant offices or client locations, depending on project or client needs.**
- Candidate must be legally authorized to work in the United States without the need for employer sponsorship, now or at any time in the future**
- We're excited to meet people who share our mission and can make an impact in a variety of ways. Don't hesitate to apply, even if you only meet the minimum requirements listed. Think about your transferable experiences and unique skills that make you stand out as someone who can bring new and exciting things to this role.
Benefits: Cognizant offers the following benefits for this position, subject to applicable eligibility requirements:
- Medical/Dental/Vision/Life Insurance
- Paid holidays plus Paid Time Off
- 401(k) plan and contributions
- Long-term/Short-term Disability
- Paid Parental Leave
- Employee Stock Purchase Plan
Create a free Caio profile to unlock more results and save your role and location preferences.
Unlock free search