AI engineer for agentic systems

Opsfleet; United States; Remote; USD 140,000 - 210,000; Full time

Job summary

Opsfleet ищет талантливого AI-инженера с опытом в Data Science, ML и Backend для работы над GenAI и автономными агентами. Ваша задача — проектировать и внедрять системы, использующие LLM и современные платформы, чтобы предоставлять масштабируемые AI-решения клиентам по всему миру.

В роли удалённого инженера вы будете заниматься архитектурой MAS, управлением контекстом и безопасностью исполнения, сотрудничая с командой инженеров и заказчиками, соблюдая высокие стандарты качества.

Qualifications

• 5+ лет Python с упором на модульную архитектуру и чистый код
• Экспертное владение современными оркестрационными фреймворками: LangChain, LangGraph, Agno, Strands, ADK
• Глубокий опыт работы с AWS Bedrock или GCP Vertex AI для корпоративного развёртывания моделей
• Практический опыт с MCP для соединения агентов с источниками данных и инструментами, A2A для межагентного взаимодействия
• Умение работать с Knowledge Graphs и векторным хранением для основы рассуждений агентов

Responsibilities

• Архитектура и развёртывание сложных Multi-Agent Systems с автономным рассуждением
• Дизайн стратегий управления контекстом: скользящие окна, семантическое суммирование, эффективная обрезка токенов
• Работа с интерфейсами MCP для взаимодействия агентов с API, БД и локальными средами
• Разработка надёжного управления состоянием долгосрочных задач с LangChain/LangGraph/ADK
• Обеспечение Production Safety: санация вывода, механизмы предотвращения ошибок/галлюцинаций
• Построение слоёв памяти: пользовательские предпочтения и контекстная история
• Определение требований к оценке агентной деятельности и верификации последовательности рассуждений

Skills

Python

Distributed/Modular architecture

Cross-functional collaboration

Explainable AI

Tools

AWS Bedrock

GCP Vertex AI

LangChain

LangGraph

MCP

A2A

Vector storage

Job description

Описание:

We are seeking a talented and experienced AI Engineer with a background in Data Science, Machine Learning, Backend development, or equivalent to join our professional services team of over 60 engineers, headquartered in Israel. The position is available full-time. This remote-first role focuses on Generative AI, specifically working with advanced Large Language Models (LLMs) and building AI agents. You'll work with state-of-the-art foundation models through platforms like AWS Bedrock and GCP Vertex AI to develop innovative GenAI applications and scalable AI infrastructure for our clients.

Задачи:

Architect and deploy complex Multi-Agent Systems (MAS) that move beyond basic RAG into autonomous reasoning, planning, and execution.

Design and implement dynamic Context Management strategies, including sliding windows, semantic summarization, and token-efficient pruning to maintain long-term coherence without exceeding model limits.

Expertise in Function Calling and Tool Definition; specifically creating standardized interfaces using MCP for agents to interact with external APIs, databases, and local environments.

You will be responsible for designing and implementing robust state-handling for long-running agentic tasks using LangChain, LangGraph, Agno, Strands, ADK, etc.

Design and implement Production Safety Measures, including output sanitization, hallucination triggers, and autonomous circuit breakers to ensure reliability in high-stakes environments.

Build sophisticated memory layers that manage User Preferences and historical context, ensuring agents provide personalized, context-aware interactions over time.

Define and implement rigorous requirements for Agentic Evaluation, benchmarking trajectory consistency, tool-calling accuracy, and reasoning logic.

Требования:

5+ years of Python experience with a focus on Modular Architecture and clean code principles. Expert-level proficiency in modern orchestration frameworks (LangChain, LangGraph, Agno, Strands, ADK, etc.). Deep experience with AWS Bedrock or GCP Vertex AI for enterprise-scale model deployment and agent hosting. Hands-on experience with MCP for connecting agents to diverse data sources and tools, and A2A for cross-agent collaboration. Proficiency in using Knowledge Graphs and vector storage to ground agentic reasoning and provide structured organizational memory.

• Direct experience working with AgentCore architectures and native Agent Engines (AWS Bedrock Agents / GCP Vertex AI Agent Engine)
• Experience building agents capable of synthesizing information across Text, Vision, and Video sources
• You can explain the difference between a linear chain and a directed acyclic graph (DAG), and you know exactly when an agent is the right tool vs. a simple workflow
• Experience conducting deep technical reviews of AI implementations, identifying architectural bottlenecks or "lazy" agent logic
• You’ve dealt with agents getting stuck in infinite loops or hallucinating tool-calls, and you know how to build the infrastructure to prevent it
• Experience with Software Factories or the AI-Driven Development Lifecycle (AI-DLC), meaning agentic pipelines where coding agents plan, write, test and review code with engineers in the loop

Условия:

You aren't just following tutorials; you are architecting the blueprint for how autonomous systems reason, collaborate, and execute.

Work on everything from internal coding agents to massive client-facing multi-agent orchestrators.

A culture built by engineers, for engineers.

Full-time position (40 hours/week) Potential career paths Collaborative remote team environment Opportunity to contribute to open-source GenAI initiatives and research publications