Ericsson
Master Thesis: Semantic Guardrails for Autonomous Networks - Verification of Constraint Preservation
Be an Early Applicant
Develop an AI-based Semantic Assurance Agent for autonomous networks. The thesis will investigate semantic equivalence chains to verify that AI agent transformations preserve original guardrails and constraints, identify acceptable deviations, and detect constraint breaches. Responsibilities include designing the experimental setup and comparing the agent’s results against a baseline.
Join our Team
About this opportunity:
Future autonomous networks will increasingly rely on AI agents that transform high-level operator intents into network optimization decisions and executable configurations. We need to ensure that during all the transformations the associated guardrails and constraints are verified and enforced. In this master thesis you have the opportunity to explore the creation and use of semantic equivalence chains (e.g. "I want to close my account" -> "user-terminated subscription" -> POST /api/v1/billing/cancel) to verify that guardrails are followed and constraints are not broken.
What you will do:
You will need to create an AI-based "Semantic Assurance Agent" that will check that any decisions (i.e. agentic transformations) based an initial intent respect the original constraints and guardrails. You will explore creating and using semantic equivalence chains (starting from the decision input or output) to attempt to recognize additional guardrail deviations and constraint breaches than a direct input and output comparison. You will also need to explore the definition of what an "acceptable" guardrail deviation is.
The skills you bring:
Why join Ericsson?At Ericsson, you'll have an outstanding opportunity. The chance to use your skills and imagination to push the boundaries of what's possible. To build solutions never seen before to some of the world's toughest problems. You'll be challenged, but you won't be alone. You'll be joining a team of diverse innovators, all driven to go beyond the status quo to craft what comes next.
What happens once you apply? Click Here to find all you need to know about what our typical hiring process looks like.Encouraging a diverse and inclusive organization is core to our values at Ericsson, that's why we champion it in everything we do. We truly believe that by collaborating with people with different experiences we drive innovation, which is essential for our future growth. We encourage people from all backgrounds to apply and realize their full potential as part of our Ericsson team. Ericsson is proud to be an Equal Opportunity Employer. learn more.
Primary country and city: Sweden (SE) || Stockholm
Req ID: 791334
About this opportunity:
Future autonomous networks will increasingly rely on AI agents that transform high-level operator intents into network optimization decisions and executable configurations. We need to ensure that during all the transformations the associated guardrails and constraints are verified and enforced. In this master thesis you have the opportunity to explore the creation and use of semantic equivalence chains (e.g. "I want to close my account" -> "user-terminated subscription" -> POST /api/v1/billing/cancel) to verify that guardrails are followed and constraints are not broken.
What you will do:
You will need to create an AI-based "Semantic Assurance Agent" that will check that any decisions (i.e. agentic transformations) based an initial intent respect the original constraints and guardrails. You will explore creating and using semantic equivalence chains (starting from the decision input or output) to attempt to recognize additional guardrail deviations and constraint breaches than a direct input and output comparison. You will also need to explore the definition of what an "acceptable" guardrail deviation is.
The skills you bring:
- General Programming skills
- An inquisitive mindset
- Knowledge of AI concepts or an active interest to independently expand your knowledge on the relevant topics.
- Designing the experimental setup and the baseline comparison of your "Semantic Assurance Agent" output.
Why join Ericsson?At Ericsson, you'll have an outstanding opportunity. The chance to use your skills and imagination to push the boundaries of what's possible. To build solutions never seen before to some of the world's toughest problems. You'll be challenged, but you won't be alone. You'll be joining a team of diverse innovators, all driven to go beyond the status quo to craft what comes next.
What happens once you apply? Click Here to find all you need to know about what our typical hiring process looks like.Encouraging a diverse and inclusive organization is core to our values at Ericsson, that's why we champion it in everything we do. We truly believe that by collaborating with people with different experiences we drive innovation, which is essential for our future growth. We encourage people from all backgrounds to apply and realize their full potential as part of our Ericsson team. Ericsson is proud to be an Equal Opportunity Employer. learn more.
Primary country and city: Sweden (SE) || Stockholm
Req ID: 791334
Similar Jobs at Ericsson
3 Days Ago
Cloud • Information Technology • Internet of Things • Machine Learning • Software • Cybersecurity • Infrastructure as a Service (IaaS)
Master’s thesis investigating how agentic AI in Snowflake CoWork can identify Critical Data Elements using metadata, data lineage, and business context. The student will review relevant literature, evaluate AI-generated recommendations against expert assessments, analyze risks and limitations, and develop recommendations for enterprise data governance integration. The project involves data governance, data quality, enterprise analytics, and potentially SQL, Python, and Snowflake.
Top Skills:
Agentic AiGenerative AiPythonSnowflakeSnowflake CoworkSQL
Cloud • Information Technology • Internet of Things • Machine Learning • Software • Cybersecurity • Infrastructure as a Service (IaaS)
Build and operate scalable data pipelines and event-driven workflows for Ericsson’s AI-powered RAN engineering platform. Responsibilities include ingestion, transformation, validation, orchestration, data quality, metadata, lineage, governance, secure handling, analytics enablement, observability, and performance optimization. The role uses Python, SQL, Prefect, Bash, AWS services, CI/CD, and containerization while collaborating with architects, engineers, product teams, and leadership.
Top Skills:
Amazon S3Aws AthenaAws BatchAws Ecs FargateAws EventbridgeAws GlueAws LambdaAws Step FunctionsBashBi DashboardsCi/CdContainerizationData CataloguesData GovernanceData LakesData LineageData WarehousesEvent-Driven Data PipelinesMetadata ManagementMonitoringObservabilityPrefectPythonRelational DatabasesSQL
Cloud • Information Technology • Internet of Things • Machine Learning • Software • Cybersecurity • Infrastructure as a Service (IaaS)
Supports end-to-end delivery of Ericsson RAN software Solution Packages from requirements and specifications through development, testing, and customer deployment. Defines objectives, scope, timelines, and deliverables; prioritizes user stories; leads process milestones; manages risks and dependencies; facilitates stakeholder communication; reports project performance; and contributes to Agile and Lean continuous improvement.
Top Skills:
AgileBaseband SoftwareLeanRanTelecommunications
What you need to know about the Manchester Tech Scene
Home to a £5 billion digital ecosystem, including MediaCity, which consists of major players like the BBC, ITV and Ericsson, Manchester is one of the U.K.'s top digital tech hubs, at the forefront of advancements in film, television and emerging sectors like as e-sports, while also fostering a community of professionals dedicated to pushing creative and technological boundaries.
