Forward Deployed AI Engineer

JobOverview

The Forward Deployed AI Engineer is a hands-on builder responsible for designing, building, and deploying agentic AI capabilities and workflows across AGS's business operations and software development processes. This role works at the frontier of what's possible with large language models and multi-agent systems building the AGS One / RevMax sales copilot, regulatory monitoring agent, AI-assisted QA testing agent, and SDLC automation tools that make up the core of AGS's AI transformation program. Agents are standardized on Azure AI Foundry as the primary runtime so they are reusable, governed, and discoverable across teams rather than one-off builds.

Responsibilities

• BuildanddeployagenticAIcapabilitiesandworkflowsmulti-stepagentsthatreason,usetools,andtakeautonomousactions,builtwithLangGraphandhostedonAzureAIFoundryAgentService(AGS'sstandardruntime);useCrewAI,AutoGen,orequivalentframeworksonlywhereaworkflowgenuinelyoutgrowsFoundry
• OwnAItoolingdeploymentCursor,Factory.AI,GitHubCopilot,ClaudeCodeintegratingAIcodingtoolsintoAGS'sdevelopmentworkflowsandmeasuringproductivityimpact
• BuildanddeploytheAGSOne/RevMaxsalescopilotAIagentsthatquerySalesforce,pullgameperformancedata,generateproposals,andsupportaccountmanagersacrosstherevenuelifecycle
• Buildanddeploytheregulatorymonitoringagentanagentthatmonitorsregulatoryfeeds,classifiesrelevantchanges,assessesbusinessimpact,androutesalertstotherightteams
• BuildAI-assistedQAtestingworkflowsautomatedtestexecution,pre-certificationcompliancechecking,andtestreportgenerationforgamebuilds,alongsideOmniBet-basedportingtools
• OwnAIpipelineorchestrationdesignandmaintaintheworkflowsconnectingLLMs,datasources,vectordatabases,anddownstreamapplications
• ImplementRAGsystemsretrieval-augmentedgenerationusingAzureAISearch(orequivalentvectorstore)foragentsthatneedtoreasonoverAGS'sproprietarydata(gameportfolio,performancehistory,regulatorydatabase)asitissurfacedthroughFabric/OneLake
• Designagenticdeploymentinfrastructurecontainerization,APIendpoints,versioning,andmonitoringforallproductionAIagents,registeredintheAzureAIFoundry/Entraagentregistry
• BuildandconsumeMCPserverintegrationsconnectagentstointernalAPIs,datasources,andtoolsviaModelContextProtocolserverssocapabilitiesarereusableacrossagentsratherthanrebuilteachtime
• Implementevaluationframeworksmeasureagentaccuracy,reliability,latency,andcost;builddashboardsthatsurfacethesemetricstotheHeadofAI
• StaycurrentonagenticAIdevelopmentsevaluatenewLLMcapabilities,orchestrationframeworks,anddeploymentpatterns;bringrelevantadvancesintoAGS'splatform

Skills/Requirements

• 48yearsofsoftwareengineeringexperience,withthelast13yearsspecificallyfocusedonLLMapplicationdevelopmentandagenticAIsystems
• ProductionagenticAIexperiencehasbuiltandshippedAIagentstoproduction,notjustprototypedemos;ideallyusingLangGraph(AGS'sprimaryframework),orLlamaIndex,CrewAI,orAutoGen
• StrongPythondevelopmentskillsproduction-qualityPythonforagentdevelopment,APIintegration,dataprocessing,anddeployment
• LLMAPIexperiencehands-onexperiencewithAnthropicClaude,OpenAI,orequivalentLLMAPIs(viaAzureAIFoundryordirect)includingfunctioncalling,tooluse,andstructuredoutput
• RAGsystemexperiencehasbuiltretrieval-augmentedsystemswithvectordatabases(e.g.,AzureAISearch,Pinecone,pgvector);understandsembeddingmodels,chunkingstrategies,andretrievaloptimization
• Promptengineeringskillssystematicapproachtopromptdesign,versioning,andevaluation;understandschain-of-thought,few-shot,andstructuredoutputprompting
• APIandsystemsintegrationexperienceintegratingwithSalesforce,databases,RESTAPIs,andenterprisesystemsfromwithinagentworkflows
• MonitoringandobservabilityexperienceinstrumentingAIapplicationsforproductionmonitoringincludinglatency,cost,andqualitymetrics
• Bachelor'sdegreeinComputerScience,Engineering,orequivalentpracticalexperience

Preferred

• ExperiencewithSDLCtoolingdeploymentandCI/CDintegration
• Familiaritywithgamingdomaingamemechanics,certificationprocesses
• ExperiencewithresponsibleAIpractices,guardrails,content-safetybaselines,andauditlogging
• FamiliaritywithMicrosoftCopilotStudio,AzureAIFoundryagentregistry,orsimilaragentgovernance/deploymentpatterns
• ExperiencebuildingorconsumingModelContextProtocol(MCP)servers

Note:Alloffersarecontingentuponsuccessfulcompletionofabackgroundcheck

*Postedpositionsarenotopentothirdpartyrecruitersandunsolicitedresumesubmissionswillbeconsideredfreereferrals.

AGSisanequalopportunityemployer