Remote AI/ML Engineer - Agent Tools & Semantic Retrieval

Sii Poland; Katowice; Remote; PLN 160,000 - 240,000; Full time

Benefits offered by this job

Great Place to Work

Solid financial situation

Centre of internal trainings

Many experts you can learn from

Profit sharing

Regular integration events and trips

Comfortable and well-equipped offices

MySii app

Medical care

Job summary

Sii Poland is seeking an experienced AI/ML Engineer to join the team for agent engineering in a remote position. You will build tools for AI agents, define schemas, and ensure seamless integration with the Semantic Retriever while deploying structured interfaces for multi-agent workflows.

You will implement complex prompts and generate structured LLM outputs, and write comprehensive unit tests. Requires 5+ years of software/AI experience, Python, Pydantic, and advanced English; residency in

Qualifications

• 5+ years of experience in software engineering or AI/ML
• Proficiency in Python and Pydantic schema development
• Expertise in API orchestration and tool architecture
• Practical knowledge of LangGraph and semantic retrieval integration
• Ability to implement complex prompts and generate structured LLM outputs
• Advanced English
• Residing in Poland required

Responsibilities

• Building and developing tools for AI agents and defining their schemas
• Ensuring seamless integration with the Semantic Retriever
• Deploying and configuring structured interfaces for multi-agent workflows
• Implementing complex prompts and generating structured LLM outputs
• Writing comprehensive unit tests for all developed solutions

Skills

Python

Pydantic schema development

API orchestration

LangGraph

Semantic retrieval integration

Prompts design & structured LLM

English proficiency

Tools

LangGraph

Job description

Sii Poland is seeking an experienced AI/ML Engineer to join the team for agent engineering in a remote position. You will build tools for AI agents, define schemas, and ensure seamless integration with the Semantic Retriever while deploying structured interfaces for multi-agent workflows.

You will implement complex prompts and generate structured LLM outputs, and write comprehensive unit tests. Requires 5+ years of software/AI experience, Python, Pydantic, and advanced English; residency in