Principal AI Engineer (Bellevue)

To get the best candidate experience, please consider applying for a maximum of 3 roles within 12 months to ensure you are not duplicating efforts.Job CategorySoftware EngineeringJob DetailsAbout SalesforceSalesforce is the #1 AI CRM, where humans with agents drive customer success together. Here, ambition meets action. Tech meets trust. And innovation isn’t a buzzword — it’s a way of life. The world of work as we know it is changing and we're looking for Trailblazers who are passionate about bettering business and the world through AI, driving innovation, and keeping Salesforce's core values at the heart of it all.Ready to level-up your career at the company leading workforce transformation in the agentic era? You’re in the right place! Agentforce is the future of AI, and you are the future of Salesforce.We are seeking a highly skilled AI Platform Engineer to play a pivotal role in building the next generation of our ML/AI platform that doesn't just support ML models, but powers autonomous AI agents at enterprise scale. This role sits at the intersection of platform infrastructure and agent systems engineering. You'll build and maintain the core infrastructure, CI/CD pipelines, and platform services that underpin our machine learning initiatives and go further in designing the harnesses, sandboxes, and evaluation frameworks that let AI agents be developed, tested, and trusted in production.You'll work on systems that directly impact marketing, sales, service, and product growth verticals across the organization.This isn't a traditional infrastructure role. You should be comfortable wearing multiple hats of software engineering, agent systems design, and evaluation tooling. We're looking for engineers who think in flywheels: build evaluate improve ship repeat.What You’ll DoAgent Harness & Flywheel EngineeringDesign and build agent harness infrastructure: the scaffolding that wraps LLM calls, manages tool use, handles retries, enforces policy, and feeds results back into iterative improvement loops.Implement agentic loop patterns with multi-turn reasoning, tool orchestration, memory management, and structured output handling as reusable platform primitivesBuild the agent flywheel: automated pipelines that collect agent traces, surface regressions, route failures to evaluation, and close the loop from production signal back to prompt/model improvementOwn the end-to-end lifecycle from agent experiment to production deployment, including versioning, rollout controls, and rollback mechanismsSandboxing & Safe ExecutionBuild sandboxed execution environments for agent tools with isolating code execution, API calls, and file system access so agents can act without unconstrained blast radiusDesign tiered autonomy models: define which actions agents can take automatically, which require human approval, and which are off-limits and enforced at the infrastructure layerImplement replay and dry-run capabilities so new agent versions can be tested against real traces before going liveAgent Evaluation, Observability & OptimizationImplement evaluation frameworks for agent behavior using a combination of vendor , open source or in house built tools — covering task success, tool selection accuracy, trajectory evaluation, hallucination rates, latency, and costBuild and maintain eval datasets, golden trace libraries, and regression test suites that run automatically on every agent code changeInstrument agent traces end-to-end: LLM calls, tool invocations, intermediate reasoning, final outputs — surfaced in Grafana or equivalent observability toolingDefine and track agent quality metrics over time; own the signal that tells the team whether agents are getting better or worseDrive continuous quality, latency, and cost improvements across deployed agents by closing the loop between production traces, evaluations, and agent design. Optimization may be done through a variety of techniques e.g. prompt tuning, tool calling optimizations, context engineering, right-sizing model selection per task and explore distillation or fine-tuning (SFT, DPO, RLHF) on curated trace data to name a fewValidate every optimization through A/B tests, shadow deployments, and replay against golden traces, with the eval suite gating rollout so wins are real and regressions are caught before they reach usersCI/CD & Workflow AutomationBuild and optimize CI/CD pipelines (GitHub Actions, ArgoCD) that cover not just code deployment but agent evaluation gates — no agent ships without passing its eval suiteAutomate Docker and package builds, security scanning, and agent integration tests as first-class pipeline stepsDesign self-healing CI patterns where agent-based automation can diagnose and fix common pipeline failuresTooling, Developer Experience & ArchitectureBuild internal tools and developer self-service interfaces that let ML engineers and data scientists iterate on agents without platform team involvementMaintain a comprehensive view of how all platform components -> infrastructure, agent harnesses, evaluation pipelines, observability — work togetherCreate architecture diagrams and drive long-term platform vision; own the how does this scale to 10x conversationMonitoring, Security & ReliabilityEstablish alerting (Grafana, PagerDuty) for both traditional platform health and agent-specific signals (error rates, tool call failures, eval score drift)Ensure all agent infrastructure adheres to security best practices: sandboxed execution, auditable traces, access controls on every toolParticipate in security reviews; own compliance for agent workloadsWhat We’re Looking For9+ years as a Platform Engineer, ML Infrastructure Engineer, or Software EngineerDemonstrated experience building agent harness infrastructure using agentic loops, tool orchestration, structured output handling, multi-turn conversation managementHands-on experience with agent evaluation frameworks like Braintrust, LangSmith, or equivalent , including building eval datasets, running automated regression suites, and tracking quality metrics over timeStrong understanding of sandboxing and safe agent execution like isolation patterns, tiered autonomy, blast radius controlsExperience with context Engineering as it relates to Agent orchestration.Strong Python engineering skills for building scalable tools, automation, and platform componentsDeep expertise in AWSExtensive experience with CI/CD tooling, especially GitHub Actions and ArgoCDProficiency in infrastructure-as-code (Terraform)Experience with containerization (Docker) and orchestration (Kubernetes)Experience with AgentOps concepts and production Multi Agent systemsStrong problem-solving skills and ability to manage multiple priorities across a complex platformPreferred Qualifications (Bonus Points):Experience with Salesforce Ecosystem including Agentforce and Data360Experience with unstructured databases(vector or graph databases) and RAG pipelinesExperience working with modern data platforms and real-time processing frameworks, including cloud data warehouses (e.g., snowflake), streaming technologies (e.g. kafka, flink)Unleash Your PotentialWhen you join Salesforce, you’ll be limitless in all areas of your life. Our benefits and resources support you to find balance and be your best, and our AI agents accelerate your impact so you can do your best. Together, we’ll bring the power of Agentforce to organizations of all sizes and deliver amazing experiences that customers love. Apply today to not only shape the future — but to redefine what’s possible — for yourself, for AI, and the world.AccommodationsIf you need a reasonable accommodation during the application or the recruiting process, please submit a request via this Accommodations Request Form.Please note that Salesforce uses artificial intelligence (AI) tools to help our recruiters assess and evaluate candidates’ resumes and qualifications throughout the recruiting process. Humans will always make any candidate selection and hiring decisions. Please see our Candidate Privacy Statement for more information about how we use your personal data and your rights, including with regard to use of AI tools and opt out options.Posting StatementSalesforce is an equal opportunity employer and maintains a policy of non-discrimination with all employees and applicants for employment. What does that mean exactly? It means that at Salesforce, we believe in equality for all. And we believe we can lead the path to equality in part by creating a workplace that’s inclusive, and free from discrimination. Know your rights: workplace discrimination is illegal. Any employee or potential employee will be assessed on the basis of merit, competence and qualifications – without regard to race, religion, color, national origin, sex, sexual orientation, gender expression or identity, transgender status, age, disability, veteran or marital status, political viewpoint, or other classifications protected by law. This policy applies to current and prospective employees, no matter where they are in their Salesforce employment journey. It also applies to recruiting, hiring, job assignment, compensation, promotion, benefits, training, assessment of job performance, discipline, termination, and everything in between. Recruiting, hiring, and promotion decisions at Salesforce are fair and based on merit. The same goes for compensation, benefits, promotions, transfers, reduction in workforce, recall, training, and education.In the United States, compensation offered will be determined by factors such as location, job level, job-related knowledge, skills, and experience. Certain roles may be eligible for incentive compensation, equity, and benefits. Salesforce offers a variety of benefits to help you live well including: time off programs, medical, dental, vision, mental health support, paid parental leave, life and disability insurance, 401(k), and an employee stock