About this role
XenonStack seeks a Machine Learning Engineer, Agentic Systems to design, develop and deploy autonomous AI agents for enterprise workflows. The full-time role is listed in Mohali, India, with a salary of 8-15 LPA.
Responsibilities
- Build and optimize agents using frameworks such as LangChain, LangGraph, CrewAI or AutoGen. Develop multi-agent workflows with shared memory, context management and task orchestration.
- Fine-tune and integrate LLMs, including OpenAI, Anthropic, LLaMA and Mistral models, for reasoning, planning and decision-making. Build tool-using agents that connect to APIs, databases and third-party services.
- Use Model Context Protocol (MCP) and A2A messaging for orchestration, and implement hybrid reasoning and retrieval pipelines combining vectors and knowledge graphs.
- Improve inference performance and operational cost; add guardrails, monitoring and evaluation for reliable agent behavior. Collaborate with product, platform and data engineering teams to integrate agents into enterprise systems and deploy them to cloud, edge or on-device environments as needed.
Qualifications
- A bachelor’s or master’s degree in Computer Science, AI/ML or a related field, plus 1–3 years of AI/ML engineering experience with direct LLM and agentic AI development experience.
- Proficiency in Python and agent frameworks; experience with RAG pipelines, vector databases such as Pinecone, Weaviate or Milvus, and knowledge graphs. Understanding of distributed systems, API integration and cloud-native architectures, and familiarity with AI observability and monitoring.
- Strong problem-solving, analytical thinking, communication and collaboration skills, with the ability to translate business workflows into autonomous AI solutions.
Benefits listed include access to certifications and advanced AI/ML workshops, performance-based incentives, recognition for innovation, medical insurance, additional allowances for project-based roles and a cab facility for women employees.
Skills for this role
PythonLangChainLangGraphCrewAIAutoGenLarge Language ModelsMulti-agent systemsRAGVector databasesPineconeWeaviateMilvusKnowledge graphsModel Context ProtocolAgent-to-Agent messagingAPI integrationDistributed systemsCloud-native architectureLLM fine-tuningInference optimizationAI observabilityAI evaluationOpenAIAnthropicLLaMAMistralProblem-solvingAnalytical thinkingCommunicationCollaboration