System DesignLLM Serving

Serving LLM Inference for a FinTech App with 100k Monthly Users

Design an LLM inference system for a FinTech app with 100k users. Focus on latency, cost, and reliability using NVIDIA and AWS tools.

Aug 31, 20264 min readOriginal analysis
Fig. 01 — Architecture
User requests flow through the app to the TensorRT model, with data security and monitoring layers.
01

The scenario

A FinTech company is launching an AI-driven personal finance assistant feature, serving 100,000 active monthly users. The assistant provides financial advice via a chat interface, requiring low-latency responses and high availability. The team consists of six engineers with a budget of $50,000/month. Regulatory compliance requires data encryption and audit logging.

If the system fails, user trust could be severely damaged, leading to high churn rates. Additionally, financial advice must be accurate and timely, or it risks regulatory scrutiny. The company aims for a 99.9% availability and a maximum response time of 1 second per query.

02

Requirements

  • R1Handle 200 QPS at peak times
  • R2p99 latency under 1 second
  • R3Budget cap at $50,000/month
  • R499.9% system availability
  • R5Data encryption and audit logging
  • R6Scalable to 2x current load
03

The design

3.1Model Serving

We will deploy the LLM using NVIDIA TensorRT Model Connect for its optimization capabilities and ease of deployment. Given the early maturity of this tool, extensive testing will be necessary to ensure stability. The models will be hosted on AWS EC2 instances using NVIDIA A100 GPUs to balance performance and cost.

3.2Load Distribution

AWS SageMaker with Multi-AZ support will manage model hosting to ensure high availability. By distributing model instances across different availability zones, we can achieve compliance with the 99.9% availability requirement. SageMaker's SchedulingConfig will help in efficiently managing resources and costs.

3.3Monitoring and Observability

Elastic Observability integrated with OpenTelemetry will be used to monitor latency, availability, and quality. This setup will allow us to establish SLOs and set up burn rate alerts to preemptively address performance issues. This will involve some operational overhead but is manageable within our team size.

3.4Data Security

AWS KMS will handle data encryption, ensuring all user data in transit and at rest is encrypted. Audit logging will be integrated into the application layer to record all user interactions for compliance purposes.

04

Capacity math

MetricValue
Peak QPS200 req/s
GPU Cost$25,000/month
Storage Cost$2,000/month
Observability Cost$1,500/month
05

Trade-offs

Inference Optimization

Picked

TensorRT Model Connect

Passed on

Custom Model Optimization

Reduces complexity and time to deploy, despite early maturity concerns.

High Availability

Picked

AWS SageMaker Multi-AZ

Passed on

Single AZ Deployment

Ensures compliance with availability SLOs.

Monitoring Stack

Picked

Elastic with OpenTelemetry

Passed on

Custom Monitoring Solution

Provides deep insights with manageable overhead.

06

Failure modes

What breaksSymptomMitigation
Model Latency SpikesIncreased p99 latency alertsUse Elastic alerts to trigger auto-scaling in SageMaker.
Data BreachUnauthorized access logsKMS encryption and regular audits.
Service DowntimeHigh error rates in telemetryDeploy Shadow Engine Recovery for fast recovery.

Editor's Verdict

This design opts for proven tools like NVIDIA TensorRT and AWS SageMaker to balance performance and cost, with a focus on meeting stringent latency and availability requirements. While the design is intentionally conservative to ensure reliability, scaling to 10x users will necessitate a reevaluation of GPU resources and possibly adopting newer, more cost-effective hardware.

Many teams underestimate the operational overhead of integrating observability tools like Elastic and OpenTelemetry, but this investment is crucial for maintaining SLOs. The most common pitfall is neglecting to plan for data security and compliance from the outset, which this design addresses through AWS KMS and audit logging.

Related LLM Serving coverage

One design a week

The next blueprint lands Tuesday.

Plus the week's AI/ML data engineering news, curated. Free.