Exavalu · Remote · United States
Experience:12+ Years |Type:Full-Time
We are seeking ahands-on AI Technical Architectwith strong experience inGenerative AI and Multi-Agentic AIto design and implement enterprise AI solutions from POC through production. The role requires expertise in agent orchestration, RAG, LLMs, enterprise integrations, cloud, and AI governance.
DesignMulti-Agentic AI architecturesusing agents, supervisors, planners, routers, and orchestration frameworks.
Build AI solutions usingPython, LangChain, LangGraph, CrewAI, and LLM APIs.
DesignRAG solutions, including embeddings, vector search, retrieval, and prompt optimization.
Integrate AI agents with enterprise applications, APIs, databases, and tools.
Design scalable cloud-native AI solutions usingmicroservices, Docker, and Kubernetes.
Establish AIsecurity, governance, observability, evaluation, and LLMOps/MLOpspractices.
Lead POCs, architecture reviews, technical decisions, and mentor AI engineering teams.
12+ years of overall technology experience.
Strong hands-on experience with Generative AI and Multi-Agentic AI.
Advanced Python programming.
Strong hands-on experience with LangChain and LangGraph.
Experience with CrewAI or similar agent frameworks.
Strong knowledge of LLMs, RAG, embeddings, vector databases, prompt engineering, and tool/function calling.
Experience with APIs, microservices, and enterprise integrations.
Experience with Azure, AWS, or GCP.
Strong understanding of AI security, Responsible AI, governance, and guardrails.
MCP and agent interoperability.
Hugging Face / Open-source LLMs.
LangSmith, Langfuse, MLflow, or OpenTelemetry.
Docker/Kubernetes and LLMOps/MLOps.
Semantic Kernel, AutoGen, or similar frameworks.
Experience building enterprise AI platforms or AI Centers of Excellence.
Core Skills: Multi-Agentic AI | Generative AI | LangChain | LangGraph | CrewAI | Python | RAG | LLMs | MCP | Vector Databases | Cloud
Originally posted on Himalayas