Your impact
Responsibilities:
- Will be responsible for developing data and document integration and ingestion pipelines from external systems (i.e. Sharepoint, Projectwise, REST APIs, etc.), processing and grooming of the data/documents to be optimized for LLMs, and utilizing various LLMs for analysis.
- Will be responsible for tuning, refine and customize LLM models behavior, to better suit specific tasks and data.
Here's what you'll need
- 2+ years experience with developing data and document integration and ingestion
- Experience with Large Language Models (LLMs).
- Strong engineering background, preferred in fields such as Computer Science, Mathematics, Software Engineering, Physics, and Data Science.
- Working knowledge on PySpark
- Strong coder with shown proficiency in programming languages such as Python, Java, C++, TypeScript/JavaScript, or similar.
- Fluent English. Preferred
You will get extra points if you have:
- Experience with RAG, Prompt Engineering and LLM tuning techniques.
- Experience in Data Engineering, Data Analytics, and/or Data Science.
- Experience integrating systems and through APIs or other techniques.
We offer:
- Unique company culture fostering individual career growth and work-life balance
- Full-time employment contract/b2b contractwith salary corresponding to qualifications
- Hybrid working model
- Flexible working hours (we start between 7:30-10:00)
- “Short Fridays” (we work 6h on Friday)
- Flexible benefits package (Lux Med medical care, psychological care, life insurance, My Benefit cafeteria system, including Multisport card co-financing, car park sharing system)
- Membership in Jacobs employee networks (Women's Network, OneWorld, PRISM, Careers Network, Green Team, Toastmasters, Collectively and others)
- Continuous development opportunities, including a range of professional trainings and certifications (e.g. ACCA, CIPS), Graduate Development Program, Learners’ Community, self-learning platform
- Opportunity to take part in language courses (English, German, Polish)