About the role

Develop and maintain AI-assisted pipelines for automated documentation generation using self-hosted LLMs and RAG architectures. Collaborate with cross-functional teams to integrate vector search, graph queries, and automated validation scripts to ensure high-quality output.

What they look for

Python Machine Learning Artificial Intelligence LLM RAG Vector databases Qdrant Neo4j Prompt engineering Git Docker CI/CD Asynchronous programming REST APIs Data science Software development

Requirements

Requires 3+ years of professional software development or data science experience with at least 1.5 years in LLM/AI applications. Candidates must possess high proficiency in Python, RAG architectures, and modern engineering practices like Docker and CI/CD.

Benefits

Premium medical package MyBenefit cafeteria platform Internal events Udemy access Language courses Company-paid certifications Flexible working hours Full remote working possibilities

Full description

Ciklum is looking for an Artificial Intelligence / Machine Learning Engineer to join our team full-time in Poland.

We are a custom product engineering company that supports both multinational organizations and scaling startups to solve their most complex business challenges. With a global team of over 4,000 highly skilled developers, consultants, analysts and product owners, we engineer technology that redefines industries and shapes the way people live.

About the role:

As an Artificial Intelligence / Machine Learning Engineer, become a part of a cross-functional development team engineering experiences of tomorrow.

The Legacy Code Semantic Documentation Project is a 26-week enterprise initiative for a global industrial automation leader. The primary objective is to engineer an automated, AI-assisted pipeline to generate structured, system-level Markdown documentation directly from an undocumented ~400K LOC codebase (spanning IEC 61131-3 languages and ANSI C/C++).

Operating within a dedicated, zero-data-egress secure tenant, the technical architecture combines Tree-sitter AST parsing, Neo4j knowledge graphs, Qdrant vector search, and self-hosted open-weight LLMs (Llama 3.1 / Mixtral family) with NLI-based validation. Delivery is structured across 7 work packages executing over a 6-month period, governed by strict contractual KPIs: ≥95% code coverage, ≥92% NLI-verified factual precision, and ≥90% SME validation acceptance. All outputs align with EU Cyber Resilience Act (EU CRA) requirements for SBOM and source-level traceability.

Responsibilities:

AI Pipeline Development: Implement and maintain multi-pass LLM generation workflows using self-hosted open-weight models (Llama 3.1, Mixtral)
RAG Retrieval Integration: Connect vector search routines (Qdrant) and graph queries (Neo4j) into unified prompt context builders
Evaluation Pipeline Support: Integrate automated NLI checking scripts to filter low-confidence generations and verify factual precision
Prompt Engineering & Templating: Construct, benchmark, and refine domain-specific prompts to output structured Markdown assets
Cross-Functional Collaboration: Partner with Data Engineers on schema ingestion and work with QA to validate AI-generated output quality against code baselines

Requirements:

Professional Experience: 3+ years in commercial software development or data science, with 1.5+ years building and deploying practical LLM/AI applications
Core Technical Stack: High proficiency in Python, clean code principles, REST APIs, and asynchronous programming
Practical AI/RAG Exposure: Demonstrated working knowledge of RAG architectures, prompt design, and vector databases (Qdrant/OpenSearch)
Model Execution Understanding: Familiarity with self-hosted open-weight LLM workflows, token management, and inference engines (vLLM, TGI)
Engineering Best Practices: Hands-on experience with Git, Docker containerization, unit testing, and CI/CD pipelines
Language: Professional proficiency in English (B2+/C1)

What’s in it for you?

Strong community: Work alongside top professionals in a friendly, open-door environment
Growth focus: Take on large-scale projects with a global impact and expand your expertise
Tailored learning: Boost your skills with internal events (meetups, conferences, workshops), Udemy access, language courses, and company-paid certifications
Endless opportunities: Explore diverse domains through internal mobility, finding the best fit to gain hands-on experience with cutting-edge technologies
Flexibility: Enjoy flexibility – full remote working possibilities
Care: We've got you covered with company-paid premium medical package through Luxmed
Benefits: Access the MyBenefit cafeteria platform, allowing you to choose perks that best suit your lifestyle and needs

About us:

At Ciklum, we are always exploring innovations, empowering each other to achieve more, and engineering solutions that matter. With us, you’ll work with cutting-edge technologies, contribute to impactful projects, and be part of a One Team culture that values collaboration and progress.

With delivery centers in Wrocław and Gdańsk, our 300+ professionals in Poland drive forward-thinking solutions for global clients. Join a community where collaboration sparks innovation—and your impact reaches millions.

Explore, empower, engineer with Ciklum!

Interested already? We would love to get to know you! Submit your application. We can’t wait to see you at Ciklum.

#LI-AD1