AI Developer
- Роль
- AI / ML
- Опыт
- Синьор
- Занятость
- Полная занятость
В объявлении не сказано, откуда нанимают. Проверьте описание или сайт работодателя перед откликом.
Ключевые навыки
Обязательные навыки
Role OverviewWe are looking for an experienced AI/ML Engineer with strong software engineering expertise and hands-on experience in Generative AI, LLMs, agentic systems, and production AI applications. You will be responsible for designing scalable AI architectures, developing multi-agent workflows, building production-grade RAG systems, integrating enterprise tools and data, and optimizing AI applications for performance and reliability.ResponsibilitiesDesign and develop multi-agent AI systems with planning, state management, tool usage, and self-correction capabilities.Build agentic workflows using frameworks such as LangGraph, AutoGen, CrewAI, or custom orchestration.Implement MCP (Model Context Protocol) servers/clients, tool calling, and API integrations with enterprise systems.Develop scalable and low-latency RAG pipelines using vector databases, hybrid search, semantic caching, and re-ranking.Implement LLM evaluation, observability, tracing, and guardrails using tools such as Ragas and Langfuse.Develop high-performance asynchronous Python microservices and optimize latency, context usage, and inference performance.Explore and implement local model serving, fine-tuning, and quantization where appropriate.Mentor junior engineers and contribute to technical architecture and engineering best practices.RequirementsBachelor's degree (Required)4+ years of professional backend development in Python.Strong experience with FastAPI, asyncio, and microservice architectures.Hands-on experience with OpenAI, Anthropic Claude, Gemini, Llama, Mistral.Experience with LangGraph, AutoGen, CrewAI, or custom agent orchestration frameworks.Experience with Pinecone, Weaviate, Qdrant, Milvus, hybrid search, semantic retrieval, and re-ranking.Knowledge of relational and NoSQL databases and enterprise data integrations.Experience building or integrating MCP servers/clients, tool calling, and APIs.Experience with Docker, Kubernetes, AWS/GCP/Azure, and CI/CD pipelines.Exposure to monitoring, tracing, evaluation, guardrails, hallucination mitigation, and production AI observability.SkillsPythonFastAPILangGraphPineconeDocker
Чем предстоит заниматься
- Design and develop multi-agent AI systems with planning, state management, tool usage, and self-correction capabilities.
- Build agentic workflows using frameworks such as LangGraph, AutoGen, CrewAI, or custom orchestration.
- Implement MCP (Model Context Protocol) servers/clients, tool calling, and API integrations with enterprise systems.
- Develop scalable and low-latency RAG pipelines using vector databases, hybrid search, semantic caching, and re-ranking.
- Implement LLM evaluation, observability, tracing, and guardrails using tools such as Ragas and Langfuse.
- Develop high-performance asynchronous Python microservices and optimize latency, context usage, and inference performance.
- Explore and implement local model serving, fine-tuning, and quantization where appropriate.
- Mentor junior engineers and contribute to technical architecture and engineering best practices.
Что требуется
- Bachelor's degree (Required)
- 4+ years of professional backend development in Python.
- Strong experience with FastAPI, asyncio, and microservice architectures.
- Hands-on experience with OpenAI, Anthropic Claude, Gemini, Llama, Mistral.
- Experience with LangGraph, AutoGen, CrewAI, or custom agent orchestration frameworks.
- Experience with Pinecone, Weaviate, Qdrant, Milvus, hybrid search, semantic retrieval, and re-ranking.
- Knowledge of relational and NoSQL databases and enterprise data integrations.
- Experience building or integrating MCP servers/clients, tool calling, and APIs.
- Experience with Docker, Kubernetes, AWS/GCP/Azure, and CI/CD pipelines.
- Exposure to monitoring, tracing, evaluation, guardrails, hallucination mitigation, and production AI observability.