AI Engineer II ( AI Platform)

MeridianLink

9d•$104,148 - $177,600•Remote

About The Position

This AI Engineer II is a mid-level engineering role responsible for designing, developing, testing, and maintaining AI platform components that enable MeridianLink's products to deliver AI-powered features consistently and reliably. You will work within the AI platform team to implement services such as model integration layers, retrieval-augmented generation infrastructure, prompt management systems, and evaluation pipelines. This role collaborates closely with Senior and Staff engineers on architecture, works directly with product engineering teams to understand their AI integration needs, and helps establish the standards and patterns teams follow when building on top of the AI platform.

Requirements

3–5 years of professional software engineering experience
Strong proficiency in backend engineering using Python, C#/.NET, Java, or Node.js
Solid understanding of algorithms, data structures, and system design principles
Hands-on experience integrating large language models or ML models into production applications
Working knowledge of retrieval-augmented generation (RAG) concepts, vector databases, and embedding pipelines
Experience building or contributing to shared services or platform components
Familiarity with cloud-managed AI services (AWS Bedrock, Azure OpenAI, or equivalent)
Experience with APIs, asynchronous processing, and event-driven architectures
Bachelor's degree in Computer Science, Software Engineering, or equivalent professional experience
In-depth knowledge of one or more programming languages (Python, C#, Java, Node.js, etc.)
Strong understanding of RESTful API design and web service architecture
Proficiency with SQL and relational databases
Experience with version control (Git) and CI/CD pipelines
Ability to write well-tested, maintainable code and participate effectively in code reviews

Nice To Haves

Experience with LLM frameworks (LangChain, LlamaIndex, etc.) or prompt engineering
Familiarity with vector databases (Pinecone, Weaviate, Milvus, or similar)
Knowledge of containerization and orchestration (Docker, Kubernetes)
Experience with observability tools and designing monitoring for ML/AI systems
Prior work in regulated industries with data handling, compliance, or audit requirements
Experience with fintech, banking, or other financial services environments
Active daily use of AI-assisted development tools and understanding of their benefits and limitations

Responsibilities

Implement AI platform components — including model serving layers, retrieval infrastructure, prompt management, and output evaluation services — under the guidance of Senior and Staff engineers
Develop and maintain APIs that product teams use to integrate AI capabilities into their applications
Build observability and monitoring into platform services to track output quality, latency, cost, and system health
Contribute to design discussions and provide input on trade-offs between simplicity, reliability, and scalability
Work with product engineering teams to understand how they want to use AI capabilities and translate requirements into platform features
Participate in technical design sessions and code reviews with product teams building on the AI platform
Help identify patterns where multiple product teams are solving the same AI integration problem and consolidate that work
Contribute to documentation, reference implementations, and runbooks that help product teams adopt AI platform services
Participate in defining and enforcing integration standards — API contracts, error handling patterns, cost attribution
Mentor junior engineers (Engineer I) and help them grow their understanding of AI systems and platform design
Implement evaluation and monitoring pipelines that give teams visibility into AI output quality and model behavior
Contribute to content safety standards and compliance guardrails appropriate for a regulated financial services environment
Help design systems that properly handle PII, maintain audit trails, and meet data residency requirements in AI pipelines