Senior AI Engineer
- Remote.Bulgaria
- Remote.Georgia
- Remote.Kazakhstan
- Remote.Poland
- Алмати
- Астана
- Белград
- Варна
- Варшава
- Вроцлав
- Днепър
- Ереван
- Киев
- Клуж-Напока
- Краков
- Ларнака
- Лвов
- Лодз
- Люблин
- Одеса
- Рига
- София
- Тбилиси
- Харков
Ако сте получили информация за тази свободна позиция от нашите рекрутери, прочетете нашата Политика за поверителност на личните данни.
Project overview
Position overview
Technology stack
Responsibilities
- Design and build production grade multi agent AI systems for real world usage
- Develop end to end AI solutions from requirements definition through architecture design and deployment
- Implement agent orchestration using LangGraph or LangChain
- Design supervisor and specialist routing, agent to agent communication, and human in the loop workflows
- Design and integrate domain-specific MCP servers and external tools into agent workflows
- Build and maintain evaluation frameworks including offline and online quality monitoring
- Monitor system performance and optimize reliability, latency, quality, safety, and operational costs
- Implement observability pipelines including tracing, prompt and output logging, and evaluation tracking
- Collaborate with Product Managers and engineering teams to refine requirements and deliver production ready solutions
- Independently propose architectures, evaluate trade offs, and drive implementation with limited supervision
Requirements
- Proven experience building and operating production LLM systems used by real customers
- Ability to clearly describe a specific production LLM or agentic system personally built and shipped
- Experience designing AI systems end to end from architecture to deployment
- Hands on experience with multi agent architectures and orchestration
- Experience with LangGraph or LangChain
- Experience implementing multi agent orchestration and agent to agent communication
- Experience with tool calling and MCP integration, including domain-specific MCP servers
- Experience building human in the loop workflows
- Experience designing evaluation frameworks including golden datasets, offline evaluations, online monitoring, and LLM as a judge
- Experience measuring regressions and making engineering decisions based on evaluation results
- Experience implementing AI observability including tracing, logging, evaluation pipelines, and latency monitoring as well as guardrail monitoring
- Experience working with production AI systems in AWS environments with a focus on reliability, scalability, and cost optimization
- Ability to independently drive technical decisions and deliver solutions with minimal supervision
- English working proficiency
Nice to have
- Experience with Amazon Bedrock AgentCore
- Experience with OpenAI APIs
- Familiarity with Arize, LangSmith, or Braintrust
- Experience with A2A communication protocols
- Experience working with retrieval systems
- Experience building conversational AI systems
Търсите сходни възможности?
