Software Engineering MTS

Salesforce•San Francisco, CA

4d•Hybrid

About The Position

Salesforce is seeking Trailblazers passionate about AI, innovation, and customer success to join their Agentforce team. The Component Accessibility Team (CAT) is focused on improving software accessibility by developing AI tools that assist developers in writing accessible code. Their goal is to make accessibility an automated, in-loop part of the development process, ensuring WCAG compliance before code reaches production. This initiative is crucial for business growth, enabling Salesforce to win public-sector and enterprise contracts, and mitigating legal and regulatory risks. The CAT accessibility product is already in use, with a Prizm PR-review presubmit having reviewed thousands of pull requests and demonstrating high accuracy.

Requirements

Strong software engineering fundamentals.
Track record of shipping software (experience scales by level).
Proficiency in JavaScript/TypeScript and modern web development.
Familiarity with at least one component framework (LWC, Aura, React, Vue, etc.).
A quality mindset: use tests, metrics, and evaluation to prove functionality.
Clear written and verbal communication skills.

Nice To Haves

Hands-on experience with AI/LLM-assisted development (building agents, tools, MCP integrations, prompts, or evals).
LangSmith or similar eval tooling experience.
Working knowledge of web accessibility (WCAG 2.2, ARIA, screen readers, keyboard navigation, focus management, color contrast).
Familiarity with the Salesforce UI ecosystem (LWC, Aura, Base Components).
Experience with testing frameworks (Jest, Selenium/functional tests).
Experience with developer-tooling adoption, telemetry, or metrics-driven product work.

Responsibilities

Creating products that increase developer productivity by automating accessibility checks and fixes.
Guiding the company's web development efforts as the WCAG lead, ensuring compliance with accessibility guidelines.
Owning the full detect → diagnose → fix → verify loop for accessibility violations.
Ensuring AI solutions for accessibility are grounded in WCAG and internal standards, and heavily evaluated for trustworthiness and performance.
Building and evaluating AI-powered accessibility tools, including fix tools and agent skills.
Designing and expanding the evaluation dataset and reviewer set to prove correctness per WCAG criterion.
Treating evaluation as a first-class deliverable with a measured, defensible quality bar.
Encoding WCAG success criteria and Salesforce internal standards into the agent's knowledge base.
Expanding per-criterion coverage and growing the reviewer set to close the gap between detection and fixing.
Packaging tools into developer workflows (Claude surfaces) and driving adoption.
Remediating real Sa11y test failures and feeding learnings back into the tools.