Thesis: Hybrid agentic workflow analysis

High Level Description

Agentic coding is becoming more of a standard in the developer industry. With the usage of AI services such as OpenAI’s ChatGPT

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 a hybrid solution of local and cloud LLM models working together to both offload cloud capacity

but also cloud costs of running larger LLM models.

Project Description

In this Thesis, investigate a hybrid approach to agentic development. The investigation should propose a solution in an Agentic

harness, eg. OpenCode where a larger LLM can oversee and delegate tasks such as exploring or implementations to smaller local

models.

Purpose

In this Thesis, investigate a hybrid approach to agentic development. The investigation should propose a solution in an Agentic

harness, eg. OpenCode where a larger LLM can oversee and delegate tasks such as exploring or implementations to smaller local

models.

• Do we need specific system prompts to handle this?

References

• Llama CPP: https://github.com/ggml-org/llama.cpp

An Exciting Journey with Knightec Group

Semcon and Knightec have joined forces as Knightec Group. Together, we are Northern Europe’s leading strategic partner in

product and digital service development. With a unique combination of cross-functional expertise and a holistic business

understanding, we help our clients realize their strategies – from idea to complete solution.

Practical Information

This is a thesis position, located at our office in Sundsvall. Start date January or March 2027.

Please submit your application as soon as possible, but no later than 2026-11-30. If you have any questions, you are welcome to

contact johanna.edstrom@knightec.se. Note that due to GDPR, we only accept applications through our careers page.