4 дня назад
Middle/Senior AI Agent Developer
hhВакансия с HeadHunter. Контакт ведёт на hh.ru
Мэтч & Сопровод
Покажет вашу совместимость и напишет письмо
Описание вакансии
Текст:
TL;DR
Middle/Senior AI Agent Developer (Python/LLM): Developing production AI agents with autonomous decision-making, reasoning, tool usage, and multi-step task execution with an accent on agent planning, memory, retrieval, and evaluation. Focus on integrating LLMs, vector stores, APIs, and external tools, optimizing inference pipelines, and monitoring agent reliability, safety, and output quality.
Location: Remote from Minsk, Belarus
Company
Develop AI solutions and software projects for international clients across finance, gaming, technology, healthcare, retail, and automotive sectors.
What you will do
- Develop, implement, and optimize production AI agents for autonomous decision-making, reasoning, and tool usage.
- Build pipelines for agent planning, memory, retrieval, and multi-step task execution.
- Integrate LLMs, vector stores, APIs, and external tools to enable complex agent behaviors.
- Design prompting strategies, reasoning chains, and agent policies to improve reliability and accuracy.
- Implement evaluation frameworks and monitor agent performance, safety, robustness, and production failures.
- Optimize inference pipelines for speed, cost efficiency, and model and tool selection.
Requirements
- 3–6 years of professional experience and strong Python skills.
- Production experience with agentic AI ecosystems, including embeddings, vector search, RAG, CRAG, and GraphRAG.
- Experience with LangChain, LangGraph, CrewAI, agent testing and verification, and agentic tools.
- Knowledge of prompt and context engineering, AI-assisted coding models, and tools.
- Strong analytical, problem-solving, communication, and ownership skills.
- English sufficient for effective technical and business communication with native speakers.
Nice to have
- Experience with autonomous and deep agents, multimodal and thinking models, LLMOps, and GenAI observability.
- Knowledge of memory management, prompt caching, model and data governance, and responsible AI.
- Familiarity with cloud infrastructure, agentic patterns, MCP, and AA-protocol.
- Understanding of machine learning fundamentals, including model training, evaluation, overfitting, regularization, cross-validation, statistics, and probability.
Culture & Benefits
- Remote work options and projects for clients including PayPal, Wargaming, Xerox, Philips, adidas, and Toyota.
- Competitive compensation based on qualifications and skills.
- Career development system with clear skill qualifications.
- Medical expense and gym membership compensation, plus corporate sports competitions.
- Online English courses, internal conferences, workshops, and meetups.
- Five paid sick days per year without requiring a sick-leave certificate, along with corporate events for employees and their children.
Будьте осторожны: если работодатель просит войти в их систему, используя iCloud/Google, прислать код/пароль, запустить код/ПО, не делайте этого - это мошенники. Обязательно жмите "Пожаловаться" или пишите в поддержку. Подробнее в гайде →