Get to know us better
CodiLime is a software and network engineering industry expert and the first-choice service partner for top global networking hardware providers software providers and telecoms. We create proofs-of-concept help our clients build new products nurture existing ones and provide services in production environments. Our clients include both tech startups and big players in various industries and geographic locations (US Japan Israel Europe).
While no longer a startup - we have 250 people on board and have been operating since 2011 weve kept our people-oriented culture. Our values are simple:
- Act to deliver.
- Disrupt to grow.
- Team up to win.
The project and the team
The project involves building LLMdriven workflows to process data ingested into observability platforms. These workflows will classify filter and correlate events enrich and transform log and metric data and leverage LangChain and LangGraph to power rootcause analysis.
What else you should know:
- The team consists of less than 7 people including an architect project manager and software and network engineers.
- We use SCRUM/Agile methodology.
- Our tech stack for the project includes: Python (requests pandas matplotlib altair plotly pytest scikitlearn) LangChain LangGraph LLM (OpenAI Gemini) Embeddings & Vector Database Jupyter Streamlit docker git CI/CD pipelines
- The client is based in the US.
We work on multiple interesting projects at the time so it may happen that well invite you to the interview for another project if we see that your competencies and profile are well suited for it.
Your role
As a part of the project team you will be responsible for:
- 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
Do we have a match
As a Senior Python Software Engineer with LLMDriven Network Data Analytics you must meet the following criteria:
- 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 handson 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.
Beyond the criteria above we would appreciate the nice-to-haves:
- 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.
More reasons to join us
- Flexible working hours and approach to work: fully remotely in the office or hybrid
- Professional growth supported by internal training sessions and a training budget
- Solid onboarding with a hands-on approach to give you an easy start
- A great atmosphere among professionals who are passionate about their work
- The ability to change the project you work on