Få nya jobb via e-post
- ...High Level Description Autonomous AI coding agents increasingly rely on powerful frontier language models to understand and modify complex software systems. However, these models can be expensive to operate, while smaller and more affordable models often struggle with...
- ...test subscription. The supervisor provides Azure budget and model API access, and no company data is used. Who are we looking... ...The candidate should be comfortable with Git, basic CI/CD concepts, Python (or a similar scripting language) and containers. No prior...
- ...not intended to be production-ready systems, but rather proof-of-concept implementations suitable for experimentation and evaluation. ~... ...effectiveness of AI assistance may depend on the selected AI model, available pipeline data, logs, documentation, and other contextual...
- ...now and then, while the systems keep changing. Large Language Model (LLM) agents can now use tools and solve tasks in several steps.... ...this risk. Limitations The implementations are proof-of-concept, not finished products, and are meant for experimentation and...
- ...for example in a CI log or a pull-request comment A proof-of-concept policy layer should be implemented in a small lab and evaluated... ...study. It is not a claim that a policy is safe in general. Model poisoning, new sandbox bypasses, and compromised build infrastructure...
2.700 €/månad
...Providing excellent customer service. Maintaining high standards of hygiene and quality. You will work in a walk-in salon concept, meaning clients come directly into the salon without appointments. No need to find your own clients or manage your own booking...- ...application gives the opportunity a clear mission and room to influence priorities and success measures. The exact partner, employment model, compensation, start date and working arrangement will be explained openly during the process. Nordic Investin will make sure you...
- ...simple web application hosted in the cloud using nothing but AI prompts. For this, the AI agents must be predefined with skills and MCP (Model Context Protocol). The main goal is to find the most effective way of setting up an application with as few prompts as possible....
- ...reduced while maintaining appropriate developer control, transparency, and accountability. The expected outcome is a proof-of-concept demonstrating how risk-based AI agent workflows can support continuous application upgrades and reduce the cost and complexity of software...
- ...and Anthropic's Claude usage limits are getting tightened. Modern laptops are getting more capable of running local open-source models and possibility of delegating simpler tasks to save on cloud cost is becoming a desirable solution. This thesis aims to investigate...
- ...High Level Description AI agents connected to real infrastructure via the Model Context Protocol (MCP) or such, can already read live system state and take real action, such as scaling a Kubernetes deployment, restarting a pod, or filing a Jira ticket. What is still...
- ...agent AI orchestration architectures tailored for public administration. The study focuses on integrating specialized Large Language Model (LLM) agents with deterministic compliance controls, auditable decision trails, and cross-institutional adaptability to automate...
- ...services due to privacy and data sovereignty requirements. This thesis investigates whether locally hosted speech and language models can provide sufficient accuracy, performance, and reliability for real-time voice applications involving sensitive information. The...
- ...incomplete information, delayed responses and missed requests. Recent advances in speech-to-text, text-to-speech and large language models make it possible to build voice agents that can answer inbound calls, hold a structured conversation, collect the information...
- ...High Level Description Generative AI and Large Language Models (LLMs) have rapidly changed the possibilities for searching, interpreting, and summarizing information. However, AI-based solutions do not necessarily outperform traditional information retrieval methods...
- ...bugs, how reliable, and at what cost. Cost is a central question: AI agents are cheap to set up but every test run consumes paid model usage, while scripted tests are expensive to write and maintain but cheap to run. Project Description The work will involve setting...
- ...Swedish public authorities cannot send sensitive information to cloud LLM services. At the same time, the hardware needed to run open models that come close to the leading cloud models on-premise is expensive, and the smaller models that are affordable to run locally are...