Software Engineering, AI Systems (SMTS)

Salesforce•San Francisco, CA

3d•$148,500 - $246,000

About The Position

Join a 10-person team within Salesforce AI Labs building computer-use AI for production. The product learns from human demonstrations and turns complex workflows into repeatable automation across enterprise applications. The team works directly with customers to build and validate solutions, convert discoveries into reusable product capabilities, and take a new offering from early customer adoption through general availability. The role owns substantial systems from design through deployment and production operation, with the scale and reach of Salesforce.

Requirements

Independently owned a substantial backend service or system through design, deployment, production failures, and subsequent improvements.
Hands-on experience building and evaluating LLM-powered systems, including the ability to explain how quality and failure modes were assessed.
Ability to reason about 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 carry it through to production.
Willingness to engage directly with customers as part of engineering work, including investigating problems and discussing 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

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 identify 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 to measure task success, expose regressions, and make failures understandable.
Work with customers to understand workflows, prototype solutions, and validate results in their environments.
Investigate where automation succeeds or fails and use findings to improve the core product.
Help customers progress from their first successful workflow to repeatable, increasingly self-service adoption.
Partner with forward-deployed engineers and product management to determine which customer needs should shape the roadmap.
Own technical decisions for substantial components from initial design through production operation.
Evaluate model selection, tool use, and context management in relation to reliability, latency, and cost.
Mentor peers through design discussions and code reviews, and participate in hiring.