About the role
Design and develop scalable AI-powered backend systems for SysML-based engineering environments
Build and maintain distributed data ingestion and ETL pipelines for large-scale engineering artifacts and technical documentation
Develop and optimize LLM-powered workflows for metadata extraction, semantic analysis, and entity resolution
Implement AI agents and multi-agent orchestration workflows
Design and improve RAG-based architectures and semantic retrieval pipelines
Develop graph-based knowledge representation and traceability analysis solutions
Work with graph databases, graph processing libraries, and semantic relationship modeling
Build and optimize distributed data processing workflows using Apache Spark
Collaborate with cross-functional engineering teams to integrate AI capabilities into platform services
Design scalable and high-performance APIs and backend services
Improve system reliability, scalability, observability, and performance across distributed environments
Participate in architecture discussions and technical decision-making processes
Contribute to cloud-native infrastructure and deployment workflows
Support deployments in secure, air-gapped, or classified environments when required
Create and maintain technical documentation and engineering best practices
At least 5 years of commercial experience in software engineering, Data Engineering, or AI systems development
Experience with Golang
Hands-on experience building distributed and scalable systems
Practical experience with LLM-based applications and AI integrations
Experience building AI agents and multi-agent systems
Strong understanding of RAG architectures and semantic retrieval workflows
Strong understanding of ETL pipelines and large-scale data ingestion workflows
Experience with cloud-native infrastructure and distributed environments
Practical experience with backend platform development and API integrations
Good understanding of semantic search, entity resolution, and metadata extraction
Experience working with highly scalable and high-performance systems
Strong problem-solving and communication skills
Upper-Intermediate level of English
WILL BE A PLUS
Background in Data Engineering
Experience with distributed data processing, Apache Spark, or Apache Beam
Experience with Knowledge Graphs and graph-based semantic modeling
Familiarity with MBSE or SysML environments
Experience supporting air-gapped or classified environments
Experience with vector databases and embedding pipelines
Experience with Kubernetes and cloud platforms such as AWS, GCP, or Azure
PERSONAL PROFILE
Analytical mindset with strong problem-solving skills
Ability to work independently and in a distributed team
Adaptability to secure and classified environments
Strong communication and collaboration abilities
Passion for AI-driven engineering solutions
Are you a Senior AI Engineer passionate about building scalable AI-driven systems? Join us at Sigma Software to work on a cutting-edge platform that transforms how large-scale engineering organizations manage and analyze complex technical data.
This is a remote position with flexible locations across Europe, Ukraine, and LATAM. You will be part of an innovative team leveraging AI, semantic graphs, and distributed processing to deliver impactful solutions.
At Sigma Software, we value expertise, creativity, and collaboration. Why join us? You will work with advanced technologies, contribute to mission-critical projects, and be part of a company recognized for excellence and innovation.
CUSTOMER
Our customer operates in the EdTech industry, delivering advanced technology solutions that optimize advertising performance and audience targeting. While the name is confidential, the organization is known for leveraging cutting-edge AI and data-driven strategies to enhance campaign effectiveness and deliver measurable business impact.
PROJECT
We are developing a next-generation AI-powered Knowledge Base and Gap Analysis platform for SysML-based engineering environments. The system enables large-scale engineering organizations to ingest, structure, analyze, and reason over complex MBSE artifacts and technical documentation. It supports both cloud and secure classified environments, improving traceability, identifying gaps, and enhancing decision-making in mission-critical projects.
Originally posted on Himalayas