The Associate, AI Platform Senior Engineer (Foundation Engineering) will support the development and maintenance of core AI infrastructure within the AI Center of Excellence. This role focuses on contributing to agent development, model and prompt optimization, and backend engineering efforts. Key Responsibilities: Assist in building and testing AI agent components and workflows. Support the implementation of LLM optimization and prompt engineering techniques. Develop and maintain backend services, APIs, and integrations for AI systems deployed on AWS. Implement Model Context Protocol (MCP)-based integrations for agent tool and data access. Write clean, maintainable Python code, participate in code reviews, and contribute to sprint planning. Troubleshoot and resolve issues in existing AI infrastructure. Required Qualifications: Strong proficiency in Python. Working knowledge of agent development concepts and frameworks. Familiarity with LLM/prompt optimization techniques including RAG and basic fine-tuning. Backend development experience with APIs, databases, and service integration. Mandatory working knowledge of AWS and cloud services. Mandatory familiarity with Model Context Protocol (MCP) concepts. Bachelor's degree required; Master's degree preferred. 3+ years of experience required (5+ yearspreferred). Background or coursework in machine learning fundamentals is preferred. The role requires effective communication and collaboration within a cross-functional team environment.
For full details about this role, click “Apply on company site” to view the employer’s original posting.
Skills for this role
PythonAI Agent DevelopmentLLM OptimizationPrompt EngineeringRAGFine-tuningBackend DevelopmentAPIsAWSCloud ServicesModel Context Protocol (MCP)Machine LearningContinuous Integration and DeploymentDebuggingDevOpsSoftware Development Life Cycle
Your skill match
Checking your profile…
YOUR NEXT STEP
Get interview-ready for this role
A focused preparation guide, built around this job’s responsibilities and requirements.
✦ AI-generated guide
Preparation suggestions, not the employer’s actual interview questions. Always check the original posting for current requirements.
01
Understand the role
What matters most
AI Infrastructure Development and Maintenance
The core of this role involves building, testing, and maintaining AI agent components and backend services. You must be prepared to demonstrate proficiency in Python and AWS cloud services to ensure these systems are scalable, reliable, and well-integrated into the existing AI Center of Excellence infrastructure.
Implementation of Model Context Protocol (MCP)
The role explicitly mandates familiarity with MCP concepts. You will be responsible for implementing these protocols to facilitate agent tool and data access, requiring a clear understanding of how to bridge AI agents with external data sources and services.
LLM Optimization and Prompt Engineering
You will support the optimization of Large Language Models through techniques such as RAG and basic fine-tuning. Success requires balancing technical model performance with practical prompt engineering to improve the accuracy and utility of AI-driven workflows.
Cross-Functional Collaboration and Documentation
As part of a collaborative team, you must effectively communicate technical processes and contribute to knowledge sharing. This includes participating in design discussions, code reviews, and sprint planning to ensure alignment with broader organizational goals.
Likely challenges to think through
Navigating Evolving AI Standards
The requirement for Model Context Protocol (MCP) suggests the team is working with emerging standards. The challenge lies in the rapid pace of change in AI frameworks; prepare by demonstrating your ability to quickly learn and apply new technical specifications in a production environment.
Balancing Innovation with Enterprise Stability
Working within a large financial services organization like TIAA requires balancing the experimental nature of AI development with the need for robust, secure, and maintainable backend systems. Prepare by highlighting your experience in writing clean, well-tested code that adheres to enterprise-grade standards.
Managing Complex Agent Workflows
Building and testing AI agent components involves managing complex dependencies and data flows. You may face difficulty in debugging non-deterministic AI behaviors; prepare by discussing your systematic approach to troubleshooting and your experience with CI/CD pipelines for AI systems.
03
Practice your answers
Technical practice
Python Backend Architecture for AI Systems
What to coverExplain how you design scalable backend services in Python to support AI workloads. Discuss your approach to handling asynchronous tasks, API design, and integrating databases within a cloud-native environment.
Implementing Model Context Protocol (MCP)
What to coverDescribe your understanding of the Model Context Protocol and how it facilitates communication between AI agents and external data sources. Provide an example of how you would implement an MCP-based integration to expose a specific tool or dataset to an LLM.
LLM Optimization and RAG Strategies
What to coverCompare Retrieval-Augmented Generation (RAG) with fine-tuning for improving model performance. Explain the trade-offs in terms of latency, cost, and accuracy when choosing between these techniques for a production AI application.
AWS Infrastructure for AI Deployment
What to coverDetail your experience deploying AI models or backend services on AWS. Focus on how you manage cloud resources, ensure security, and optimize for cost and performance in an AI-focused infrastructure.
AI Agent Development Lifecycle
What to coverWalk through the process of building and testing an AI agent component. How do you ensure the agent's workflows are reliable, and what metrics do you use to evaluate its performance during the development phase?
Prompt Engineering Best Practices
What to coverDiscuss techniques for optimizing prompts to improve model output quality and consistency. Suggest how to systematically test and version control prompts within a larger software development lifecycle.
Troubleshooting AI Infrastructure
What to coverDescribe a scenario where you had to debug a performance issue or failure in an AI-integrated system. What steps did you take to isolate the problem, and how did you verify the fix?
CI/CD for AI Applications
What to coverExplain how you incorporate Continuous Integration and Deployment (CI/CD) practices into AI projects. How do you handle automated testing for code versus validation for model outputs?
Behavioural practice
Collaborating in Cross-Functional Teams
What to coverDescribe a time you worked with non-technical stakeholders or team members from different functions to deliver a project. How did you ensure clear communication and alignment on technical requirements?
Handling Technical Guidance
What to coverThe role involves working under the guidance of senior engineers. Share an example of how you have received and implemented constructive feedback on your code or design decisions in the past.
Managing Sprint Priorities
What to coverTell us about a time you had to balance multiple tasks during a sprint. How did you prioritize your work to meet deadlines while maintaining code quality?
Contributing to Knowledge Sharing
What to coverProvide an example of how you have contributed to team documentation or knowledge sharing. Why is this important in an AI development environment, and how did your contribution impact the team?
02
Sharpen your knowledge
Topics to prepare
Model Context Protocol (MCP) Architecture
The role explicitly requires familiarity with MCP for agent tool and data access. Review the protocol specification to understand how it standardizes communication between AI models and external data sources. Exercise: Map out a hypothetical architecture where an AI agent uses MCP to query a secure internal database, focusing on the request-response flow and security boundaries.
LLM Optimization and RAG Fundamentals
The position involves prompt engineering, RAG, and basic fine-tuning. Focus on the conceptual differences between these approaches and when to apply each for infrastructure efficiency. Exercise: Compare the latency and cost trade-offs of using RAG versus fine-tuning for a domain-specific knowledge retrieval task.
AI Infrastructure on AWS
The role requires backend engineering for AI systems deployed on AWS. Review core AWS services relevant to AI, such as Lambda for serverless APIs, S3 for data storage, and managed container services. Exercise: Design a simple cloud-based pipeline that triggers an LLM inference task via an API endpoint, ensuring you account for scalability and logging.
Skills to revise
Python Backend Development
You must write clean, maintainable Python code for APIs and integrations. Focus on building robust, testable services. Exercise: Develop a small Python-based REST API using a framework like FastAPI that integrates with a mock external service, ensuring you include unit tests and proper error handling.
AI Agent Component Development
The role involves building and testing agent workflows. Practice creating modular components that handle specific tasks within an agentic loop. Exercise: Build a basic agent workflow that takes a user query, retrieves context from a local file, and uses an LLM to generate a structured response.
04
Your preparation checklist
Demonstrate Model Context Protocol (MCP) proficiency
Prepare a technical explanation or a small code sample demonstrating how you have used or would use MCP to connect an AI agent to external tools or data sources. Be ready to discuss the architecture of MCP-based integrations.
Review AI infrastructure and RAG workflows
Create a summary of your experience building RAG pipelines or optimizing LLM prompts. Be prepared to explain how you handle data retrieval, context window management, and the trade-offs between different fine-tuning or optimization techniques.
Prepare AWS and backend service examples
Document specific instances where you developed and deployed Python-based APIs or backend services on AWS. Focus on how you managed cloud resources, ensured service scalability, and integrated these services into a larger AI ecosystem.
Formulate questions for the AI Center of Excellence
Prepare thoughtful questions regarding the team's current AI infrastructure stack, how they prioritize agent development projects, and how they balance rapid experimentation with the need for maintainable, production-grade code.
Availability has not yet been verified. Status can change after a check; confirm on the employer’s website. Report an issue · Our checking policy
Share this opportunityKnow someone who would be a great fit?