Remote AI/ML Engineer: Multi-Agent Workflows & Tools

Sii Poland; United States; Remote; USD 36,000 - 59,000; Full time

Benefits offered by this job

Centre of internal trainings

Profit sharing

Regular integration events

Job summary

Sii Poland is seeking an experienced AI/ML Engineer for a remote role focused on agent engineering. You will build tools, define schemas, and integrate with the Semantic Retriever to enable multi-agent workflows.

Strong Python and Pydantic schema development are essential, along with API orchestration skills and English proficiency. Candidates must reside in Poland, with a passion for cutting-edge AI solutions and a drive to contribute to structured LLM outputs and robust testing.

Qualifications

• 5+ years in software engineering or AI/ML.
• Strong Python skills and Pydantic schema development experience.
• Expertise in API orchestration and tool architecture.
• Practical knowledge of LangGraph and semantic retrieval integration.
• Advanced English required.
• Residing in Poland is required.
• Familiarity with other AI frameworks or tools is a plus.

Responsibilities

• Build and develop tools for AI agents and define their schemas.
• Ensure seamless integration with the Semantic Retriever.
• Deploy and configure structured interfaces for multi-agent workflows.
• Implement complex prompts and generate structured LLM outputs.
• Write comprehensive unit tests for all developed solutions.

Skills

5+ years experience

Python

Pydantic

API orchestration

LangGraph

English proficiency

Poland resident

Tools

Python

Pydantic schema development

Job description

Sii Poland is seeking an experienced AI/ML Engineer for a remote role focused on agent engineering. You will build tools, define schemas, and integrate with the Semantic Retriever to enable multi-agent workflows.

Strong Python and Pydantic schema development are essential, along with API orchestration skills and English proficiency. Candidates must reside in Poland, with a passion for cutting-edge AI solutions and a drive to contribute to structured LLM outputs and robust testing.