ML Engineer, Customer Memory & Retrieval (Remote)

Twilio Inc.; United States; Remote; USD 129,000 - 170,000; Full time

Benefits offered by this job

Health insurance

401(k) retirement

Paid time off

Parental leave

Sick leave

Job summary

Twilio is hiring a Machine Learning Engineer for the Conversation Memory team. You will build pipelines to turn raw conversation data into structured, searchable memory and maintain evaluation systems that ensure accuracy as the product evolves.

You will work on extracting relevant information, connecting memory to customer context, and delivering fast, accurate responses for agents across millions of conversations.

Qualifications

• Experience building backend services and quickly picking up new languages, frameworks, and tools.
• Curious approach to service management and operating systems with rigor and accountability.
• Experience building or working with evaluation/quality-measurement systems, such as regression detection or quality metrics, or the desire to learn.
• Strong grounding in observability: structured logging, metrics, and debugging distributed systems.
• Fluency with AI-assisted dev tools and critical thinking in applying them.

Responsibilities

• Build the data extraction pipeline to turn raw data into structured memory for fast access.
• Own the retrieval path that answers what we know about a person in milliseconds.
• Contribute to evaluation systems that quantify memory quality and guide improvements.
• Diagnose production issues across ingestion, extraction, and indexing paths using logs and traces.
• Partner with Product and ML teams to translate customer problems into system changes and evaluation criteria.

Skills

Backend services

Production observability

LLM prompts

Go/Python

Kafka

LLM-backed products

Evaluation systems

Job description

Twilio is hiring a Machine Learning Engineer for the Conversation Memory team. You will build pipelines to turn raw conversation data into structured, searchable memory and maintain evaluation systems that ensure accuracy as the product evolves.

You will work on extracting relevant information, connecting memory to customer context, and delivering fast, accurate responses for agents across millions of conversations.