Job Description
Key Responsibilities
Twój zakres obowiązków:
- Design and deploy agents that continuously scan scientific literature and patent databases, summarising and prioritising findings.
- Build pipelines to ingest and vector-index knowledge from Slack, Confluence/JIRA, notes and emails; implement retrieval-augmented generation.
- Integrate agents with GitHub to review pull requests, suggest fixes, analyse Sentry logs and propose solutions.
- Develop sandboxed execution environments for agents to prototype and optimise algorithms (e.g. optical flow for rBCG, DSP filters, hyper-parameter sweeps).
- Orchestrate automated experiments: ablation studies, HPO, sweeps with reproducible metrics and traceability.
- Implement guardrails, automated testing and evaluation harnesses for LLM-based agents; ensure privacy-by-design and secure access to data.
- Generate weekly executive summaries of literature, experimental outcomes and engineering insights for both technical and leadership teams.
- Analyze biosignal data to identify meaningful patterns and trends.
Requirements
Nasze wymagania:
- MSc / PhD in Computer Science, AI, Mathematics, or related field.
- 4+ years of experience in software engineering or ML, including production use of LLM frameworks (LangChain, LangGraph, CrewAI or similar).
- Strong proficiency in Python and related libraries; ability to develop complex, testable workflows.
- Hands-on experience with GCP (Cloud Storage, Vertex AI, Cloud Run/K8s), GitHub, CI/CD, Docker/Kubernetes.
- Knowledge of RAG, vector databases (Pinecone, Weaviate, pgvector) and ingestion pipelines for unstructured data.
Are you interested in this position?
Apply by clicking on the “Apply Now” button below!
#GraphicDesignJobsOnline
#WebDesignRemoteJobs
#FreelanceGraphicDesigner
#WorkFromHomeDesignJobs
#OnlineWebDesignWork
#RemoteDesignOpportunities
#HireGraphicDesigners
#DigitalDesignCareers
# Dynamicbrand guru