Description
Opportunity Description:
We’re Salesforce, the Customer Company, inspiring the future of business with AI+ Data +CRM. Leading with our core values, we help companies across every industry blaze new trails and connect with customers in a whole new way. And, we empower you to be a Trailblazer, too — driving your performance and career growth, charting new paths, and improving the state of the world. If you believe in business as the greatest platform for change and in companies doing well and doing good – you’ve come to the right place.
We are looking for a technical leader who understands that building an AI agent is only 10% of the work—the real engineering challenge is measuring it. We need a thought leader who can solve the "problem nobody talks about": evaluating non-deterministic agentic systems in production. You will lead the team responsible for defining what "good" looks like for agents, moving beyond basic accuracy to rigorous evals that bridge agent spec’s to business outcomes. You will thread together Applied Science (defining metrics, curation of golden datasets, establishing ground truth) and Product Engineering (shipping software)
Responsibilities:
Build the "Evaluation Core": Lead the engineering of a scalable evaluation platform that runs in parallel with agent execution.
Thread Science & Engineering: Operationalize applied science by turning theoretical benchmarks into production regression tests and bring about a discipline of eval driven development
Thought Leadership: Act as the internal SME for AI testing. Educate cross-functional partners (Product, UX, ML) on the difference between stochastic AI behavior and traditional deterministic software
You are an Engineering leader who can lead the group through technical leadership, process management, maintain a good discipline of high quality code delivery aided with AI tools as necessary.
You are a People leader who ensures teams have clear priorities and adequate resources. You are a multiplier and have a passion for team and team members’ success providing technical guidance, career development, and mentoring.
Required Skills:
Specialized Agent Evaluation Experience: You have specific experience building evaluation harnesses for LLMs or Agents
Applied Science & Engineering Hybrid: You have a track record of managing "Research Engineering" or "Applied Science" teams where you had to operationalize vague scientific goals into shipping code. You are comfortable curating "Golden Sets" of data and building custom benchmarks from scratch.
Deep Knowledge of Eval Methodologies: You are fluent in modern evaluation techniques, including:
- LLM-as-a-Judge: Validating judges against human ground truth to prevent self-bias.
- Behavioral Analysis: Evaluating how an agent thinks (Reasoning Traces/Chain of Thought), not just the final output.
Production-Grade AI Experience: You have shipped AI products where you had to manage real-world constraints like token budgets, inference latency, and cost-normalized accuracy. Pragmatic orientation to building ML solutions that work in production at scale
Familiarity with academic and industry benchmarks and their limitations in a business environment.
Experience building simulation environments (mock APIs, virtual users) to stress-test agents safely before deployment.
Experience with Data engineering, specifically around data acquisition, creating data pipelines, metric measurement, and analysis
Experience owning highly available services and putting processes in place to maintain uptime
Prior experience working with global teams
Strong verbal and written communication skills, organizational and time management skills
Advanced degree in Computer Science, Machine Learning, or related field with a focus on system evaluation or reliability
#LI-Y
For roles in San Francisco and Los Angeles: Pursuant to the San Francisco Fair Chance Ordinance and the Los Angeles Fair Chance Initiative for Hiring, Salesforce will consider for employment qualified applicants with arrest and conviction records.