Key Responsibilities

• Design and develop multi-agent systems where multiple AI agents collaborate, delegate, and coordinate to solve complex workflows
• Build and maintain robust backend services (APIs, microservices, data pipelines) that power AI agent infrastructure
• Develop intuitive frontend interfaces for agent monitoring, configuration, and human-in-the-loop interactions
• Integrate Large Language Models (LLMs) into agentic frameworks with tool use, memory, and planning capabilities
• Implement agent orchestration patterns including chain-of-thought reasoning, ReAct, function calling, and task decomposition
• Define evaluation frameworks to measure agent reliability, accuracy, and performance
• Collaborate with cross-functional teams to identify automation opportunities and deploy agent-based solutions

• Strong experience in multi-agent system design — orchestration, communication protocols, agent roles, and coordination strategies
• Solid backend development skills (Python, Node.js, or similar) including REST/GraphQL APIs, databases, message queues, and cloud infrastructure
• Proficient in frontend development (React, Next.js, Vue, or similar) to build dashboards, chat interfaces, and agent interaction UIs
• Hands-on experience with LLM-based agent frameworks (e.g., LangChain, LangGraph, CrewAI, AutoGen, or custom implementations)
• Strong understanding of prompt engineering, retrieval-augmented generation (RAG), and tool/function calling
• Familiarity with version control (Git), CI/CD, and containerization (Docker)

Nice-to-Have

• Deep Learning — experience with training or fine-tuning neural networks (PyTorch, TensorFlow)
• Computer Vision (CV) — working knowledge of image/video processing models and pipelines
• AutoML — experience with automated model selection, hyperparameter tuning, and ML pipeline optimization
• Deploying Local LLMs — hands-on experience running open-source models (DeepSeek, Mistral, Qwen, etc.) on-premise or on private infrastructure using tools like vLLM, Ollama, or TGI
• Optimizing LLM Inference — knowledge of quantization (GPTQ, AWQ, GGUF), batching strategies, KV-cache optimization, speculative decoding, and GPU memory management
• Experience with vector databases (Milvus, Pinecone, Weaviate, Qdrant)
• Knowledge of MLOps practices and model monitoring in production

• A problem-solving mindset with a passion for building autonomous, intelligent systems
• Ability to work across the full stack — from model integration to polished user-facing experiences
• Strong communication skills and the ability to explain complex AI concepts to non-technical stakeholders
• A self-driven attitude with a desire to stay current in the rapidly evolving AI agent landscape

What We Offer

• Competitive salary pegged to experience and market rates (rate review depends on your progress).

• Remote-first culture with a flexible schedule (sync hours overlap with California-time team).

• Hardware or cloud-GPU budget for experimentation.

*ДЛЯ ЗАКЛЮЧЕНИЯ КОНТРАКТА НУЖНО ИМЕТЬ ИП (ИНДИВИДУАЛЬНЫЙ ПРЕДПРИНИМАТЕЛЬ)

*В СОПРОВОДИТЕЛЬНОМ ПИСЬМЕ УКАЗАТЬ НЕ НИЖЕ КОТОРОГО ВЫ ГОТОВЫ RATE $ PER 1 HOUR

*РАБОТОДАТЕЛЬ НЕ РАССМАТРИВАЕТ НИКАКИХ ВОЗМОЖНЫХ СЛУЧАЕВ ПАРТАЙМА, ВЫ МОЖЕТЕ РАБОТАТЬ ТОЛЬКО С НАМИ