Middle Python Developer (ML)

Sigma Software; Warszawa; On-site; PLN 120,000 - 170,000; Full time

Job summary

SmartRecruiters, Inc. invites a software engineer to contribute to two AI initiatives: ChatCPI and a Knowledge Graph Platform. You will design and implement LLM-based features, build RAG pipelines, and optimize vector-based retrieval in a fast-growing environment.

You will process sources, structure data, and iterate to提升 AI output quality, taking ownership from design to deployment. The role requires 3+ years in software development, 2+ years in AI/ML projects, strong Python skills, and

Qualifications

• 3+ years of commercial software development experience.
• 2+ years of experience on AI/ML projects.
• Strong Python programming skills with hands-on experience.
• Hands-on experience with LLMs and modern AI technologies.
• Experience with RAG architecture, vector embeddings, and hybrid search.
• Experience processing data to improve AI quality, including data preparation, chunking, metadata enrichment, and relevance tuning.
• Ability to work independently and take ownership of tasks from design through deployment.

Responsibilities

• Design and implement LLM-based features and RAG pipelines from data ingestion to answer generation.
• Build and optimize retrieval using vector embeddings and hybrid semantic and keyword search.
• Process, clean, and structure source information to improve AI output accuracy and relevance.
• Evaluate model quality, experiment with new approaches, and bring proven solutions into production.
• Work closely with the team to integrate AI components into the wider platform.
• Own changes end-to-end, including design, implementation, testing, and deployment.
• Work independently while proactively communicating blockers, scope questions, and technical trade-offs.

Skills

Python

LLMs

RAG

Vector embeddings

Hybrid search

Data preparation

Ownership

Independent work

Job description

You will join one of two AI initiatives: ChatCPI, an LLM-powered assistant for intelligent search and question answering over large technical documentation, or a Knowledge Graph Platform focused on structuring and connecting enterprise information for AI-driven use cases.

CUSTOMER

Our Customer is a leading Swedish telecommunications company recognized for delivering innovative large-scale technology solutions across complex infrastructure environments. The company operates internationally, serving millions of users and working with global technology leaders to drive digital transformation in the telecommunications industry.

PROJECT

You will join one of two AI initiatives: ChatCPI, an LLM-powered assistant for intelligent search and question answering over large technical documentation, or a Knowledge Graph Platform focused on structuring and connecting enterprise information for AI-driven use cases.

Technologies: Python, LLMs, RAG, vector embeddings, hybrid search, knowledge graphs.

Job Description

• Design and implement LLM-based features and RAG pipelines from data ingestion to answer generation
• Build and optimize retrieval using vector embeddings and hybrid semantic and keyword search
• Process, clean, and structure source information to improve the accuracy and relevance of AI-generated output
• Evaluate model quality, experiment with new approaches, and bring proven solutions into production
• Work closely with the team to integrate AI components into the wider platform
• Own changes end-to-end, including design, implementation, testing, and deployment
• Work independently while proactively communicating blockers, scope questions, and technical trade-offs

Qualifications

• 3+ years of commercial software development experience
• 2+ years of experience working on AI/ML projects
• Good Python skills with hands‑on implementation experience
• Practical experience with LLMs and modern AI technologies
• Practical experience with RAG architecture, vector embeddings, and hybrid search
• Experience with information processing aimed at improving AI quality, including data preparation, chunking, metadata enrichment, and relevance tuning
• Ability to work independently and take ownership of tasks from design through deployment

WILL BE A PLUS

• Experience with knowledge graphs or graph databases
• Background in the telecommunications domain

By clicking the link above or any third-party link within this posting, you are leaving this site and going to a third-party website where the third-party website's terms and privacy policy apply