Software Engineering, AI Systems (SMTS)
$149k - $224k • Remote • California - San Francisco
Posted 2d ago
Job Location
California - San Francisco
Tech Stack
Remote Work Policy
Fully remote
Categories
AI Agent Engineer
About the job
Salesforce is seeking a Software Engineering, AI Systems professional to join Salesforce AI Labs. This role involves building a product that learns from human demonstrations to automate complex workflows across enterprise applications. You will tackle challenging engineering problems related to agent dependability, reasoning, and error recovery. The position offers the opportunity to work directly with customers, own substantial systems from design to deployment, and contribute to taking a new offering from early adoption to general availability, supported by Salesforce's scale.
Responsibilities
- Build systems that learn from demonstrations and combine AI reasoning with deterministic execution to complete workflows reliably.
- Develop recovery and verification capabilities for agents to 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 to measure task success, expose regressions, and make failures understandable.
- Work alongside customers to understand their workflows, prototype solutions, and validate results.
- Investigate automation successes and failures to drive improvements to the core product.
- Help customers transition toward repeatable, increasingly self-service adoption.
- Partner with forward-deployed engineers and product management to shape the product roadmap.
- Own technical decisions for substantial components from design through production operation.
- Evaluate model selection, tool use, and context management against reliability, latency, and cost.
- Mentor peers through design discussions and code reviews, and participate in hiring.
Requirements
- Independently owned a substantial backend service or system through its lifecycle.
- Hands-on experience building and evaluating LLM-powered systems, including assessing quality and failure modes.
- Ability to reason through concurrency, persistent state, retries, and partial failures in consequential systems.
- Proficiency in Python, Go, Java, or JavaScript/TypeScript.
- Ability to translate unclear customer problems into bounded technical approaches, test with users, and deliver to production.
- Desire for direct customer engagement, including problem investigation and technical tradeoff discussions.
- Thoughtful use of AI development tools and responsibility for correctness, security, and maintainability.
- 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.