Senior Software Development Engineer in Test - AI Tooling & Automation

Salesforce•San Francisco, CA

10d

About The Position

Salesforce is seeking an enthusiastic Senior Software Development Engineer in Test (SMTS) with an AI-first approach to build and maintain validation for AI-driven software. The role involves transitioning from traditional testing to leveraging AI for acceleration and accuracy, acting as a multiplier with AI tools. The engineer will play a key role in defining and implementing the product's quality strategy, collaborating with cross-functional teams including product development and AI teams to ensure Salesforce's AI solutions meet high-quality standards for enterprise applications. Prior experience with agentic products is a plus.

Requirements

Strong technical fundamentals of Java, particularly in data structures and algorithms.
Hands-on experience evaluating Large Language Models (LLMs) for quality response, including familiarity with GPT-like models and AI evaluation frameworks is a big plus.
Proven track record of delivering automation solutions in a fast-paced CI/CD environment, supporting rapid deployment schedules without compromising quality.
Excellent communication skills, with the ability to work cross-functionally with product managers, engineers, AI/ML engineers, and data scientists.
Strong analytical and problem-solving abilities with a focus on identifying quality gaps and driving improvement.

Nice To Haves

A software engineer with a strong coding background and understanding of delivering software at pace in Agentic PDLC.
Strong experience with white-box testing and fixing code is a huge plus.
Experience working with public cloud infrastructure (AWS/Azure/GCP) and/or foundational knowledge of the Salesforce platform (Salesforce Certifications are a plus).
Prior experience testing autonomous agents, conversational UIs, or generative AI workflows.

Responsibilities

Design, build, and maintain scalable, AI-first testing frameworks and automation suites to validate complex workflows and agentic capabilities.
Translate high-level quality strategies into actionable automation plans, focusing heavily on validating LLM integrations, prompt accuracy, and deterministic system behaviors.
Dig deep into the application code to understand system architecture, identify quality gaps, perform white-box testing, and actively contribute to fixing code and test flakiness.
Implement and support evaluation processes for subjective quality dimensions of our AI features, including response relevance, user safety, and contextual accuracy.
Partner closely with developers, product managers, and engineers to ensure quality is integrated early and continuously throughout the agile delivery lifecycle.