Sr AI Agent Engineer

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

Job summary

LexsiLabs in Bengaluru, India, is building a high-autonomy AI Engineering Agent to execute end-to-end AI engineering workflows atop the Lexsi backend. You will design the core agent architecture, decide how the agent reasons, plans, executes actions, and ensures inspectability and alignment from day one.

The role requires deep hands-on engineering, ownership from day one, and the ability to operate in ambiguous environments while delivering robust, auditable, and scalable systems for real-world

Qualifications

• Significant experience shipping AI/ML-heavy systems.
• Hands-on experience with agentic AI systems and frameworks (ReAct, AutoGPT, LangChain).
• Strong backend engineering with Python, APIs, databases and cloud familiarity.
• Systems thinking mindset and ability to reason about performance, reliability and safety as intertwined constraints.

Responsibilities

• Own the architecture and implementation of the AI Engineering Agent.
• Build robust tool orchestration and execution layers for reliable internal and external integrations.
• Design and implement memory and state management for long-running tasks.
• Embed alignment, safety, and interpretability into system design with research team involvement.
• Stress-test agent behavior in real-world conditions and iterate for reliability.

Skills

Agentic AI systems

Python backend

API design

Ambiguous environments

Tools

ReAct

AutoGPT

LangChain

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.