Sr AI Agent Engineer

Story Terrace Inc.; Bengaluru; On-site; INR 3,500,000 - 6,000,000; Full time

Job summary

LexsiLabs is building a high-autonomy AI engineering agent lab in Bengaluru to execute end-to-end AI workflows atop our backend. The role demands hands-on engineering to define how the agent reasons, plans, and executes with memory and state across long horizons.

You will own core architecture decisions, ensure interoperability with internal services, APIs, and data systems, and drive safety, alignment, and interpretability in production environments.

Qualifications

• Significant experience building and shipping complex AI/ML systems.
• Hands-on experience with agentic AI systems and frameworks (ReAct, AutoGPT, LangChain, LangGraph, Semantic Kernel).
• Strong backend engineering fundamentals with Python, APIs, databases, and cloud.
• Systems-thinking mindset for performance, reliability, cost, safety, and interpretability.
• Comfort working in ambiguous, fast-moving environments.

Responsibilities

• Own the architecture and implementation of the AI Engineering Agent.
• Build robust tool orchestration and execution layers.
• Design and implement memory and state management for long-running tasks.
• Embed alignment, safety, and interpretability into system design.
• Stress-test agent behavior in real-world conditions.
• Set a high engineering bar and participate in design discussions.

Skills

AI system design

Agent architectures

Python programming

Backend APIs

Memory management

Tools

LangChain

ReAct

AutoGPT

LangGraph

Semantic Kernel

Job description

LexsiLabsisafrontierAIlabfocusedonbuildingaligned,interpretable,andsafesuperintelligentsystems.Ourworkspansalignmentmethodologies,interpretability-ledsystemdesign,andfoundationalmodelresearchacrossstructured,tabular,andenterprisedata.WebuildAIsystemsintendedforreal-worlddeployment,wheretransparency,auditability,androbustnessarefirst-classconstraints.

Weoperatewithaflatstructure,highautonomy,andastrongbiastowardengineerswhotakefullownershipofwhattheybuild,fromarchitecturetoproductionbehavior.

TheRole

Wearebuildingahigh-autonomyAIEngineeringAgentthatcanexecuteend-to-endAIengineeringworkflowsontopoftheLexsibackend.Thesystemisdesignedtoreasonovercomplexobjectives,planmulti-stepactions,interactwithtoolsanddatasystems,evaluateoutcomes,anditerateoverlonghorizonswhileremaininginterpretableandaligned.

AsaSrAIAgentEngineer,youwillberesponsiblefordefiningandbuildingthecoreagentarchitecture.Youwillmakefoundationaldecisionsabouthowtheagentreasons,plansandexecutesactions,maintainsmemoryandstate,andhasitsdecisionsinspectedandexplained.Thisrolerequiresdeephands-onengineeringandtheabilitytooperateinambiguousenvironmentswithownershipfromdayone.

WhatYou'llBuild

• End-to-endAIEngineeringAgentsthatcanautonomouslyperformtaskssuchasexperimentdesign,evaluation,analysis,andreporting,ratherthanmerelyassistingahumanintheseworkflows.
• HarnessEngineering:Abletodesignandmaintaincomplexharnesscomponentsthatsupportagents'scaleexponentiallyforcomplextasks.
• Agentarchitecturesthatcombinereasoning,planning,toolorchestration,andmemory,withexplicithandlingoflong-horizonexecution,partialfailures,andself-correction.
• DeepintegrationswiththeLexsibackend,includinginternalevaluationsystems,datapipelines,andalignmenttooling,aswellasenterpriseAPIsandproprietarydatasources.
• Agentsdesignedforenterpriseandregulatedenvironments,whereeveryaction,decision,andoutputmustbeinspectable,explainable,anddefensible.

Responsibilities

• OwnthearchitectureandimplementationoftheAIEngineeringAgent,makingearlydesigndecisionsaroundplanners,reasoningloops,memorymodels,andexecutioncontrolthatwillshapethesystemlong-term.
• Buildrobusttoolorchestrationandexecutionlayers,ensuringtheagentcaninteractreliablywithinternalservices,externalAPIs,anddatasystems,andrecovergracefullyfromfailures.
• Designandimplementmemoryandstatemanagement,enablingagentstooperateacrosslong-runningtasks,retainrelevantcontext,andreasonoverpastactionsandoutcomes.
• Embedalignment,safety,andinterpretabilityintothesystemdesign,workingcloselywithresearchteamstoensurethatagentbehaviorisauditableandcontrollablebyconstruction.
• Stress-testagentbehaviorinreal-worldconditions,identifyingedgecases,failuremodes,anddistributionshifts,anditeratingonthesystemtoimprovereliabilityandcorrectness.
• Setahighengineeringbar,contributingtodesigndiscussions,codereviews,andtechnicaldecision-makingwithastrongsenseofownershipandaccountability.

Requirements

• SignificantexperiencebuildingandshippingcomplexAIorML-heavysystems,whereyouhaveownedarchitectureandseensystemsevolveinproduction,notjustprototypes.
• Hands-onexperiencewithagenticAIsystemsandframeworks,suchasReAct-styleagents,AutoGPT-likesystems,LangChain,LangGraph,SemanticKernel,orsimilar,withaclearunderstandingoftheirlimitationsandfailuremodes.
• Strongbackendengineeringfundamentals,includingadvancedPythonproficiency,experiencebuildingAPIsandservices,andfamiliaritywithdatabases,datapipelines,andcloudinfrastructure.
• Asystems-thinkingmindset,withtheabilitytoreasonaboutperformance,reliability,cost,safety,andinterpretabilityasinterconnecteddesignconstraints.
• Comfortworkinginambiguous,fast-movingenvironments,whereproblemsarelooselyspecifiedandownershipisexpectedratherthanassigned.

StrongBonusSignals

• Experiencebuildinglong-horizonorstatefulagentsystemsthatmustreasonovertimeratherthansingle-turninteractions.
• PriorexposuretoAIalignment,interpretability,orsafetytooling,especiallyinproductionorenterprisesettings.
• Experienceworkinginregulatedorhigh-stakesdomains,wheresystembehaviormustbeexplainedandauditedafterdeployment.
• Atrackrecordofdebuggingandimprovingsystemsthatbehavedunpredictablyintherealworld.

Wemovequicklyandexpectcandidatestodothesame.Wevaluesubstanceoverpolishandexecutionoverrhetoric.