Software Engineer, AI Systems (PMTS)

Salesforce•Boston, MA

4d•$172,500 - $344,700

About The Position

Join a 10-person team within Salesforce AI Labs bringing computer-use AI into production. The team is building Systems Integration Agent, which learns to operate enterprise applications and turns complex workflows into reusable, code-backed automation. Customers are already using workflows in production, and the team is working to make that success repeatable across more systems and use cases. The role focuses on making computer-use agents dependable in production: determining whether an agent succeeded, deciding when it should reason versus follow deterministic paths, and recovering from application changes or requesting human help before consequential mistakes. The engineer will work directly with customers to build and validate solutions, then turn discoveries into reusable product capabilities. As a hands-on Principal Engineer, the role shapes architecture across agent and backend systems, owns critical capabilities from design through operation, and helps other engineers deliver them.

Requirements

Experience leading the architecture and delivery of complex backend systems through deployment, production failures, and subsequent improvements, with impact across multiple components or teams.
Hands-on experience shipping and operating LLM-powered systems, and ability to explain how evaluations and production failures informed design decisions.
Ability to reason through concurrency, persistent state, retries, and partial failures in systems that perform consequential actions.
Proficiency in Python, Go, Java, or JavaScript/TypeScript.
Ability to turn an unclear customer problem into a bounded technical approach, test it with users, and lead it through production while creating capabilities other engineers can build on.
Willingness to engage directly with customers, investigate problems, and discuss technical tradeoffs.
Thoughtful use of AI development tools and responsibility for the correctness, security, and maintainability of shipped work.

Nice To Haves

Experience with agent tool use, code generation, automated recovery, or evaluation frameworks.
Experience with browser automation, workflow orchestration, or enterprise integrations.
Experience building an early-stage product or working in a customer-facing engineering role.

Responsibilities

Design and build systems that learn from demonstrations and combine AI reasoning with deterministic execution to complete workflows reliably.
Develop recovery and verification capabilities that help agents adapt to changes, confirm outcomes, and recognize when human intervention is needed.
Build backend services with robust workflow state management, failure handling, and secure access to customer environments.
Create evaluations and diagnostics that measure task success, expose regressions, and make failures understandable.
Work alongside customers to understand workflows, prototype solutions, and validate results in their environments.
Investigate where automation succeeds or fails and turn findings into improvements to the core product.
Help customers move from their first successful workflow toward repeatable, increasingly self-service adoption.
Partner with forward-deployed engineers and product management to determine which customer needs should shape the roadmap.
Lead architectural decisions across agent execution, backend services, and workflow state, aligning system boundaries and tradeoffs with other technical leads.
Evaluate model selection, tool use, and context management against reliability, latency, and cost.
Raise the engineering bar through hands-on implementation, design reviews, and mentoring; help engineers take on broader ownership and participate in hiring.