Requirements

Expected technologies

Python

Optional technologies

Splunk

Graylog

Docker

Kubernetes

Our requirements

• At least 5 years of Python development experience focusing on data processing and visualizations using tools such as requests, pandas, matplotlib, altair, plotly, jupyter, pytest or similar.
• At least 1 year of hands‑on experience with LLM-based workflows, including prompt engineering, LangChain and LangGraph usage, embeddings, RAG/VectorDB integration, and automated or semi-automated testing of these workflows.
• Intermediate machine learning skills, especially in classification, clustering, and time-series analysis using scikit-learn or comparable frameworks.
• 1 year of experience applying AI techniques to network and IT infrastructure data— using knowledge on device behavior across layers and protocols, and leveraging their syslog and telemetry outputs for advanced observability.
• Intermediate proficiency with Linux, including shell scripting, environment setup, log inspection, and basic tooling use.
• English language skills at B2 level or higher.

Optional

• Familiarity with syslog processing workflows and log management tools like Splunk or Graylog.
• Knowledge of frameworks tailored to LLM output testing (DeepEval, BenchLLM, LangSmith, OpenAI Evals, TruLens).
• Proven experience in developing interactive Streamlit applications.
• Experience with containerization and orchestration, including Docker and Kubernetes for packaging, deployment, and scaling.
• Advanced ML capabilities, including deep learning or statistical modeling frameworks like PyTorch, TensorFlow, or statsmodels.

Your responsibilities

• Designing and orchestrating LLM-driven workflows tailored to syslog and telemetry analysis
• Crafting clear, structured prompts to ensure well-formatted and reliable LLM outputs
• Validating responses for relevance and accuracy, and fine-tuning prompts and workflows accordingly
• Developing and integrating tools (e.g., topology lookups, telemetry APIs) and verifying their correct use by LLM agents
• Building data transformation and enrichment pipelines for syslog and telemetry preparation
• Proposing and iterating on workflow steps and feedback loops to continuously improve accuracy
• Implementing data chunking strategies to accommodate LLM context limitations
• Writing automated tests to cover prompts, tool integration, and edge-case behavior
• Consulting with network domain experts to review and refine LLM-based RCA results