Forward Deployed AI Engineer

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 / Rev Max 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

• BuildanddeployagenticAIcapabilitiesandworkflows—multi-stepagentsthatreason,usetools,andtakeautonomousactions,builtwith
  
  Lang Graphandhostedon Azure AIFoundry Agent Service (AGS'sstandardruntime);useCrewAI,Auto Gen,orequivalentframeworksonlywhereaworkflowgenuinelyoutgrowsFoundry
• OwnAItoolingdeployment—Cursor,Factory.
  
  AI,Git Hub Copilot ,Claude Code—integratingAIcodingtoolsintoAGS'sdevelopmentworkflowsandmeasuringproductivityimpact
• BuildanddeploytheAGSOne/Rev Maxsalescopilot—AIagentsthatquery
  
  Salesforce,pullgameperformancedata,generate proposals,andsupportaccountmanagersacrosstherevenuelifecycle
• Buildanddeploytheregulatorymonitoringagent—anagentthatmonitorsregulatoryfeeds,classifiesrelevantchanges,assessesbusinessimpact,androutesalertstotherightteams
• BuildAI-assistedQAtestingworkflows—automatedtestexecution,pre-certificationcompliancechecking,andtestreportgenerationforgamebuilds,alongside
  
  OmniBet-basedportingtools
• OwnAIpipelineorchestration—designandmaintaintheworkflowsconnectingLLMs,data sources,vector databases,anddownstreamapplications
• ImplementRAGsystems—retrieval-augmentedgenerationusing
  
  AzureAISearch(orequivalentvectorstore) foragentsthatneedtoreasonoverAGS'sproprietarydata(game portfolio,performance history,regulatory database) asitissurfacedthrough
  
  Fabric/One Lake
• Designagenticdeploymentinfrastructure—containerization,API endpoints,versioning,andmonitoringforallproductionAIagents,registeredinthe
  
  AzureAIFoundry/Entraagentregistry
• BuildandconsumeMCPserverintegrations—connectagentstointernalAPIs,data sources,andtoolsvia
  
  Model Context Protocolserverssocapabilitiesarereusableacrossagentsratherthanrebuilteachtime
• Implementevaluationframeworks—measureagentaccuracy,reliability,latency,andcost;builddashboardsthatsurfacethesemetricstotheHeadofAI
• StaycurrentonagenticAIdevelopments—evaluatenewLLMcapabilities,orchestration frameworks,anddeploymentpatterns;bringrelevantadvancesintoAGS'splatform

Skills/Requirements

• 4–8yearsofsoftwareengineeringexperience
  ,withthelast1–3yearsspecificallyfocusedonLLMapplicationdevelopmentandagenticAIsystems
• ProductionagenticAIexperience
  —hasbuiltandshippedAIagentstoproduction,notjustprototypedemos;ideally using
  
  LangGraph(AGS'sprimaryframework),orLlama
  
  Index,CrewAI,orAuto Gen
• Strong Pythondevelopmentskills
  —production-quality
  
  Pythonforagentdevelopment,API integration,data processing,and deployment
• LLMAPIexperience
  —hands-onexperiencewith
  
  Anthropic
  
  Claude,OpenAI,orequivalentLLMAPIs(viaAzureAIFoundryordirect) includingfunctioncalling,tooluse,andstructuredoutput
• RAGsystemexperience
  —hasbuiltretrieval-augmentedsystemswithvectordatabases(e.g.,AzureAISearch,Pinecone,pgvector);understandsembeddingmodels,chunking strategies,andretrievaloptimization
• Promptengineeringskills
  —systematicapproachtopromptdesign,versioning,an devaluation;understands chain-of-thought,few-shot,andstructuredoutputprompting
• APIandsystemsintegration
  —experienceintegratingwith
  
  Salesforce,databases,RESTAPIs,andenterprisesystemsfromwithinagentworkflows
• Monitoringandobservability
  —experienceinstrumentingAIapplicationsforproductionmonitoringincludinglatency,cost,andqualitymetrics
• Bachelor'sdegreein
  
  Computer
  
  Science,Engineering,orequivalentpracticalexperience

Preferred

• ExperiencewithSDLCtoolingdeploymentandCI/CD integration
• Familiaritywithgamingdomain—game mechanics,certification processes
• ExperiencewithresponsibleAIpractices,guardrails,content-safety baselines,andauditlogging
• Familiarity with Microsoft Copilot Studio ,AzureAIFoundryagentregistry,orsimilaragentgovernance/deployment patterns
• Experiencebuildingorcons…