Get more replies from employers
Send a job-specific resume in minutes.
XenonStack is seeking an Agentic AI Engineer to design, develop, and deploy autonomous AI agents that can reason, plan, and act within enterprise workflows. You will work at the intersection of LLMs, reasoning systems, orchestration frameworks, and real-world integrations to deliver measurable business impact.
If you have experience in LLM-powered applications, multi-agent architectures, and building tool-augmented AI systems, this is your chance to shape the future of enterprise automation.
XenonStack is the fastest-growingData and AI Foundry for Agentic Systems, enabling people and organizations to gainreal-time, intelligent business insights.
We deliver innovation through:
Our mission is to help enterprises transform intofuture-ready, data-driven organizationsthroughCloud Native Platforms, Decision-Driven Analytics, and AI-powered solutions.
We are seeking anAgentic AI Engineerto design, develop, and deploy intelligent AI agents that can reason, plan, and act autonomously within enterprise workflows. In this role, you will work at the intersection ofLLMs, reasoning systems, orchestration frameworks, and real-world integrationsto deliver measurable business impact.
If you have experience inLLM-powered applications, multi-agent architectures, and building tool-augmented AI systems, this is your chance to shape the future of enterprise automation.
Design, build, and optimizeautonomous AI agentsusing frameworks such asLangChain, LangGraph, CrewAI, AutoGen, or similar.
Implementmulti-agent collaboration workflowswith shared memory, context management, and task orchestration.
Fine-tune and integrateLLMs(OpenAI, Anthropic, LLaMA, Mistral, etc.) for reasoning, planning, and decision-making tasks.
Developtool-using agentsthat can interface with APIs, databases, and third-party services.
Work withModel Context Protocol (MCP)andA2A (Agent-to-Agent)messaging for scalable orchestration.
Implementhybrid reasoning + retrievalpipelines (vector + knowledge graph).
Optimizeinference performanceand reduce operational costs on platforms likeNexaStack.
Implementguardrails, monitoring, and evaluationto ensure safe and reliable agent behavior.
Work closely with product, platform, and data engineering teams to integrate agents into enterprise systems.
Deploy AI agents tocloud, edge, or on-device environmentsas required.
Bachelor’s or Master’s inComputer Science, AI/ML, or related field.
2–4 years inAI/ML engineering, with direct experience inLLM and agentic AI development.
Proficiency inPythonand libraries/frameworks such as LangChain, LangGraph, CrewAI, AutoGen.
Experience withRAG pipelines, vector databases (Pinecone, Weaviate, Milvus), andknowledge graphs.
Understanding ofdistributed systems, API integration, and cloud-native architectures.
Familiarity withobservability and monitoringfor AI systems.
Strong problem-solving and analytical thinking.
Ability to translatebusiness workflows into autonomous AI solutions.
Excellent communication and collaboration skills.
Passion for exploring emerging AI capabilities and best practices.
Access to certifications and advanced AI/ML workshops.
Work oncutting-edge Agentic AI and enterprise automation projects.
Performance-based incentives and special recognition for innovation.
Additional allowances for project-based roles.
Cab facility for women employees.
At XenonStack, we cultivate agrowth-driven, people-first culturebuilt on bold leadership, collaboration, and innovation. We valuedeep work, anobsession with adoption, and a commitment to delivering solutions that are both impactful and elegantly simple.
Join us in our mission toaccelerate the world’s transition to AI + Human Intelligence, and be part of shaping how enterprises work, think, and grow.