The Experience
Join the Agentforce Optimization Agent team, where we're building the first AI-native observability platform for agentic systems. Our product analyzes millions of agent sessions in production, using advanced reasoning to surface performance bottlenecks, conversation quality issues, and optimization opportunities that would take human analysts weeks to discover.
You'll work at the intersection of distributed systems, agentic AI, and real-time analytics — shipping features that directly impact how customers understand and improve their AI agents at scale. This role spans two critical workstreams: building the Optimization Agent backend and integrating observability tooling into Agent Studio within Salesforce Core.

What You'll Actually Be Doing

• Build intelligent data pipelines: Design and implement scalable systems that query, process, and analyze agent session data from Data Cloud (STDM, Feedback DMOs) with sub-second latency requirements
• Ship Agent Studio integrations: Contribute to the Agent Developer Lifecycle (ADLC) by building UI integrations that surface optimization insights directly in the Agent Studio Sessions & Details views — working across the full stack from React frontend to backend services
• Optimize agent reasoning performance: Tackle challenging latency problems — output token optimization, reasoning step reduction, tool call chaining — to deliver a responsive user experience while maintaining analytical depth
• Build for Salesforce Core at scale: Integrate observability features into the core Salesforce platform, ensuring they work reliably across multi-tenant, multi-cloud production environments with strict security and compliance requirements
• Own features end-to-end: From backend services (Java/Python) to data queries to UI components, you'll own features from design through customer deployment

You're Our Person If...

• You have experience building and scaling distributed backend systems or platform services in a production environment, with strong proficiency in Java, Python, or a comparable language.
• You have exposure to agentic AI frameworks or LLM-integrated products.
• You bring a demonstrated, genuine AI-first approach to engineering — using AI tools (e.g., Claude Code, GitHub Copilot, Cursor) to move faster, build fluency across the stack, and contribute well beyond your core specialty.
• You have advanced prompt engineering skills and the ability to write precise, structured prompts, and cultivate the system context that makes AI outputs reliable, secure, and production-ready.
• A related technical degree required.

Even Better If...

• You have experience with intelligent systems, runtime evaluation, automated detection, or observability tooling in large-scale distributed environments.
• You've worked in a multi-cloud environment (AWS, GCP, or Azure) and understand infrastructure-level performance constraints.