About this role
The candidate will join a cross-functional team to work on the Legacy Code Semantic Documentation Project, an enterprise initiative for a global industrial automation leader. The role involves engineering an automated, AI-assisted pipeline to generate structured Markdown documentation from a large undocumented codebase. The technical stack includes Tree-sitter AST parsing, Neo4j knowledge graphs, Qdrant vector search, and self-hosted open-weight LLMs like Llama 3.1 and Mixtral. Key responsibilities include building LLM generation pipelines, implementing advanced RAG retrieval routines, and optimizing model inference under fixed compute constraints. The engineer will partner with Data Engineers and AQAs to ensure high factual precision and code coverage.
Skills & technologies
Must have
Nice to have
- Tree-sitter
- ANSI C
- C++
- IEC 61131-3
Read full description
Job Description
Ciklum is looking for a Senior Artificial Intelligence/Machine Learning Engineer to join our team full-time in Ukraine.
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 a Senior 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
LLM Pipeline Engineering: Build and optimize multi-pass generation pipelines using self-hosted open-weight LLMs (Llama 3.1, Mixtral) running on local GPU infrastructure NLI & Validation Development: Design and integrate NLI-based validation layers and automated confidence filtering to consistently meet the ≥92% factual precision threshold Context Assembly & RAG: Implement advanced RAG retrieval routines combining Neo4j graph traversal and Qdrant vector search for structured code context generation Prompt Optimization & Fine-Tuning: Develop, test, and benchmark domain-specific prompts and structured output templates for multi-level code summarization Inference Optimization: Tune model throughput, latency (p95 <30s/entity), and token budget management under fixed compute constraints Cross-Functional Support: Partner with Data Engineers to finalize pipeline data schemas and assist AQAs in defining automated test suites for AI outputs
Requirements
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.
As one of Ukraine’s largest IT companies and a top employer recognized by Forbes, we’ve spent over 20 years delivering meaningful tech solutions. We proudly support diverse talent and military veterans, recognizing their unique skills and perspectives they bring to shaping the future.
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.
Ciklum is looking for a Senior Artificial Intelligence/Machine Learning Engineer to join our team full-time in Ukraine.
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 a Senior 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
- Professional Experience: 5+ years of software/AI engineering experience, with 2+ years actively designing and deploying production-grade LLM and RAG solutions
- Mandatory AI Core Skills:
- Direct experience with LLM deployment & inference (Llama 3.1, Mixtral, vLLM, TGI)
- Demonstrated expertise in RAG architectures and hybrid retrieval strategies
- Hands-on experience with NLI (Natural Language Inference) and automated LLM evaluation tools
- Programming & Tooling: Deep technical proficiency in Python, async processing, LangChain/LlamaIndex, and AI evaluation toolkits
- Infrastructure: Familiarity with Docker, Kubernetes, GPU resource optimization, and private cloud deployment models
- Quality & Engineering Discipline: Strong focus on code quality, unit testing for AI pipelines, and systematic benchmarking
- Language: Full professional proficiency in English (C1+)
- 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 radical flexibility – work remotely or from an office, your choice
- Care: We’ve got you covered with company-paid medical insurance, mental health support, and financial & legal consultations
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.
As one of Ukraine’s largest IT companies and a top employer recognized by Forbes, we’ve spent over 20 years delivering meaningful tech solutions. We proudly support diverse talent and military veterans, recognizing their unique skills and perspectives they bring to shaping the future.
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.
Ready to apply?Apply now
