Senior Applied AI Engineer, Agentic Systems

Agilent helps laboratories around the world advance scientific discovery, diagnostics, and applied market solutions through instruments, software, consumables, services, and deep domainexpertise.

As aSeniorApplied AI Engineer, Agentic Systems, youwill beanAI engineering SMEwithin a cross-functional AIpod, working alongsidedata engineers, domain experts, businessstakeholders, and platform teams.Your role is to design, build, deploy, and governAI solutions that solverealscientific, service, commercial, and operational challenges across the enterprise.

You will work directly with the end users to understand their workflows, translate businessneeds into production-grade AI solutions, and ensure those solutions are reliable, observable, reusable, andresponsible.

This role goes beyondprototyping. You will build AI agents, RAGapplications, orchestration patterns, evaluation frameworks,and reusable skills that become part of Agilent's broader AI ecosystem.

You do not need to know Agilent's internal AIplatform terminology on day one. We are looking for someone with strong software engineering foundations, experience delivering AI applicationsinto production, and a passion for buildingpractical solutions that create measurablebusiness value.

• Define thearchitecture and build approach for the pod's use case, selectingappropriateagents, RAG,retrieval, andorchestrationpatterns; designsarereviewed with theHead of Agentic AI Platform Engineeringtoensure alignmentwith reference patternsand platform standards.

• Buildreusable AI skills and integrations using sharedplatform services and established integration patterns rather than one-off solutions, ensuring components are independentlytestable and designed for reuse, withappropriateidentity, access, and governance controls.

• Embed evaluation, testing,and observabilityinto delivery from the first sprint, definingbenchmark setswithdomain expertsandestablishingregressiontestingand productionmonitoringbefore launch.

• Implement AI solutionsin accordance withsecurity, compliance, and governancerequirements, includingrisk-basedcontrolsandhuman-in-the-loopapprovalpointsfor regulatedorGxP-relevant use cases.

• Contribute reusableskills, orchestration patterns, and evaluationassetsback to thebroader AI platform, documentingthemforfuture teams and designing withthe second consumerin mind.

• Partnerwith and upskilldomain SMEs andbusinesspractitionerswithin the pod,helping themsustainAI solutionsand providing feedback back toimproveplatformcapabilities over time.

• The pod's agentic systemislive in productionwithin the domain workflow,with documentedgovernance, identitycontrols, and human-in-the-loopprocesses whererequired.

• Evaluationcoverage isestablishedforcriticalAIbehaviors, withtesting, monitoring, and observability embedded into the delivery lifecycle.

• Multiplereusableskills,orchestrationpatterns, orevaluationassetscreated by the podhave been adopted, reused, or positioned for reuse acrossadditionaluse cases.

• A rotating SME orbusinesspractitioner from the podhas increased their AIcapabilitythroughactivecontribution to thesolution and ongoing adoption of AI-enabled ways of working.

10% of the Time

Day

No End Date

• Full-stack engineering strength with demonstrated LLM application experience in production

• Experiencebuilding agents, RAGsolutions, evaluationframeworks, observabilitycapabilities, and deploymentprocesses, notjustprototypes.

• Working familiarity with MCP or equivalent tool-use protocols, and the architecturaljudgementto build composable systems under a registry discipline rather than one-off integrations.

• High agency and tolerance for ambiguity;comfortablebeing the senior engineer in a room of scientists, service leaders, or commercial operators, treating theirexpertiseas a critical input to solution design.

• Experience or genuine willingness to operatewithinregulatedenvironments; you understand why an audit trail is a feature, not a constraint.

• Communication strong enough to demo to a VP and debug with a bench scientist in the same afternoon.

• Excellent communication and the ability to influence.Youwrite and speak clearly,adaptyour style todifferent audiences, and buildcredibilitythroughclarity rather thanauthority.

• Curiosity about AI,including both itsopportunitiesand itslimitations.You stay informedabout emerging approaches whilemaintaininghealthyskepticism and focus on responsible implementation.

• Alifelong learnerwhocontinuouslyadapts, expands skills, and embraces new ways of working in a rapidly evolving field.