Staff AI Engineer, Agentic Automation

About the company

How Jobgether works We use an AI-powered matching process to ensure your application is reviewed quickly, objectively, and fairly against the role's core requirements. Our system identifies the top-fitting candidates, and this shortlist is then shared directly with the hiring company. The final decision and next steps (interviews, assessments) are managed by their internal team. We appreciate your interest and wish you the best! Why Apply Through Jobgether?

Your tasks

• AIAgentArchitectureandProductionOwnership:Leadtheend-to-endarchitecture,development,deployment,andongoingoperationofagenticapplicationonboardingandself-healingautomationsystems.Definetechnicalroadmaps,establishproduction-readinessstandards,andtakeownershipofreliability,observability,andon-callresponsibilities.
• IntelligentApplicationOnboarding:AdvanceAIagentsthatanalyzepublicAPIdocumentationthroughheadlessbrowsersandgeneratevalidatedOpenAPIspecifications.DevelopagentsthatnavigateSaaSapplicationinterfaces,executeworkflows,andproducereliable,replayableautomationsequences.
• Self-HealingAutomation:Designsystemsthatdetectchangesinapplicationinterfaces,authenticationflows,andAPIstructuresbeforetheydisruptcustomeroperations.Buildagentsthatdiagnosefailures,repairworkflowsorspecifications,andvalidatefixesagainstrealexecutionsbeforeredeployment.
• EvaluationandQualityAssurance:EstablishandmaintainbenchmarksforgeneratedAPIspecifications,browserworkflows,andautomatedrepairs.Developevaluationharnessesandmeasurablequalitythresholdstodeterminewhenoutputsaresafeandreliableenoughforproduction.
• PerformanceandCostOptimization:Monitorandoptimizemodelaccuracy,latency,andcostpergeneratedoutput.Evaluatefrontierandopen-weightmodelsusingmeasurableperformancedatatobalancequality,efficiency,andscalability.
• SecurityandRiskManagement:DefineandimplementsecuritycontrolsforAIagentsinteractingwithsensitivecredentialsanduntrustedwebsites.Addresspromptinjection,credentialisolation,tokenmanagement,sandboxedbrowsing,andnetworkegresscontrols.Ensuresecretsareexcludedfromprompts,logs,queues,andpersistedworkflowstate.
• DistributedSystemsandWorkflowReliability:Productionizeagentsystemsusingdurableworkfloworchestrationtechnologies,suchasTemporal,andimplementrobusthandlingofretries,idempotency,asynchronousexecution,andfailures.
• Cross-FunctionalTechnicalLeadership:Collaboratewithintegration,automation-runtime,andplatformengineeringteamstoalignarchitectureandimplementation.Producecleartechnicaldesigndocumentation,guideengineeringdecisions,andmentorcontributorsasagenticautomationcapabilitiesmature.
• ContinuousImprovementandStrategicDirection:Drivetheevolutionofagenticautomationtowardincreasinglyautonomousapplicationonboardingandrecovery.Establishmilestonesforproductionadoption,reducedfailurerates,loweroperatingcosts,andminimizingtheneedformanualintervention.

Requirements

• ProductionAIEngineeringExperience:DemonstratedexperienceshippingLLM-poweredagentswithtool-usecapabilitiesthatoperateautonomouslyforrealusers,alongsideownershipofbackendsystemsinproduction.
• ProgrammingSkills:StrongproficiencyinPythonorTypeScript,withtheabilitytoworkproductivelyinbothlanguages.
• LLMAgentsandToolUse:Deepunderstandingofagentloops,structuredoutputs,toolorchestration,retries,andcommonfailuremodesinautonomousAIsystems.
• EvaluationandBenchmarking:Experiencebuildingevaluationframeworks,benchmarks,ortestingharnessesandusingquantitativeresultstoguidetechnicaldecisionsandimproveproductionquality.
• BrowserAutomationandAPIIntegrations:SignificantexperiencewithbrowserautomationtechnologiessuchasPlaywrightorcomparabletools,ordeepexpertiseinbackendandAPIintegrationsystems,combinedwiththeabilitytoworkeffectivelyacrossbothareas.
• DistributedSystems:Understandingofqueues,idempotency,durableexecution,andworkfloworchestrationplatformssuchasTemporal,AWSStepFunctions,orsimilartechnologies.
• SecurityExpertise:Strongsecurityjudgmentwhendesigningsystemsthathandlecredentialsandsensitiveinformation,includingfamiliaritywithpromptinjectionrisks,secretisolation,andsecureexecutionenvironments.
• TechnicalLeadership:Abilitytotakeearly-stagesystemsfromdevelopmenttoproductionindependently,makesoundarchitecturaltrade-offs,andensuresystemsremainreliableafterlaunch.
• CommunicationandCollaboration:Excellenttechnicalwritingskills,withtheabilitytodocumentarchitecture,communicatecomplexdecisions,influencestakeholders,andmentorengineersacrossteams.
• PreferredTechnicalExperience:Hands-onexperiencewithTemporalinproduction,PydanticAIorcomparableagentframeworks,open-weightmodelservingplatformssuchasFireworks,Together,orAmazonBedrock,andLLMcostmodeling.
• AdditionalPreferredSkills:Familiaritywithcomputer-useagents,ChromeManifestV3browserextensions,OpenAPItooling,identityandaccessmanagement(IAM),credentialmanagement,AWS,andTerraform.

What we offer

• Remotework: Opportunity to work remotely from anywhere in the United States.
• Technical ownership: Lead critical AI automation systems from early development through production and ongoing operation.
• Innovation: Work on challenging problems at the intersection of agentic AI, enterprise security, browser automation, and identity management.
• Technical influence: Shape architecture, engineering standards, evaluation frameworks, and the long-term direction of agentic automation.
• Professional growth: Develop expertise in production-grade LLM systems, distributed workflows, self-healing automation, and AI security.
• Collaborative environment: Partner with engineering specialists across integrations, platform development, and automation infrastructure.
• Meaningful impact: Help enterprises reduce manual identity-management work, improve automation reliability, and strengthen security across disconnected applications.

Other

Data Privacy Notice: By submitting your application, you acknowledge that Jobgether will process your personal data to evaluate your candidacy and share relevant information with the hiring employer. This processing is based on legitimate interest and pre-contractual measures under applicable data protection laws (including GDPR). You may exercise your rights (access, rectification, erasure, objection) at any time.