Poland onlyGet 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 we’ve kept our people-oriented culture. Our values are simple:
- Act to deliver.
- Disrupt to grow.
- Team up to win.
The project and the team
We develop software for modern platforms and operating systems for leading networking equipment manufacturers, as well as various other cloud-native, containerized services and solutions.
We are looking for an AI/ML engineer with a background in network security to validate, train, and develop AI models for security threat detection.
What else you should know:
- The client is based in the US, with some of its employees located in India
- Close cooperation with the client’s representatives will be required
- Client’s AI/ML experts are already working on the project
- Online meetings in US-friendly hours (18:00, 19:00) will be required two to three times a week
Your role
As a part of the team, your responsibility will be to:
- Develop an innovative cybersecurity product that leverages cutting-edge analytics, machine learning, and threat intelligence to provide advanced threat detection and incident response capabilities
- Preprocess network data, extract features, and build ML/DL models and pipelines for threat detection
- Evaluate ML/DL models’ efficiency, propose and implement changes to reduce false positive rates
- Develop scripts for continuous ML/DL monitoring and retraining/redeployment triggers
- Optimize ML/DL models to meet appropriate inference performance
- Explain how ML/DL models operate and why specific threats are flagged, ensuring model decisions are transparent and understandable
- Take part in technical discussions with the team and the client
Do we have a match
As a Senior AI/ML Engineer, you must meet most of the following criteria:
- Strong grasp of core ML concepts (supervised/unsupervised learning, regularization, etc.). Hands-on experience with various classic ML models (classification, regression, clustering, anomaly detection) and with DL models utilizing various neural network architectures (CNNs, RNNs, LSTMs, Transformers, etc.)
- Deep experience with PyTorch for model development, training, evaluation, and deployment. Ability to write custom layers, loss functions, and use the PyTorch ecosystem
- Experience in network security, including a deep understanding of TCP/IP, DNS, HTTP, and TLS protocols, as well as flow and PCAP data analysis for threat detection
- Advanced Python programming skills for AI/ML model development and network security analysis, including experience with core and specialized libraries for efficient data processing, feature engineering, and scalable model deployment (PyTorch, Scikit-learn, Pandas/NumPy, Scapy, etc.)
- Familiarity with containerization and cloud deployment (AWS preferred)
- Ability to work both independently and in a team
- English at least B2 level, C1/C2 preferred
A perfect match candidate will also possess the following experience:
- Experience in AI models evaluation & monitoring: imbalanced classification know‑how, live metrics for drift/skew/quality, alert volume controls, build automated retraining/redeployment triggers
- Experience in behavioral modeling with network data: applying ML techniques to analyze and model behaviors in networked or graph-structured data, ability to extract features, detect patterns, and infer relationships or anomalies within large-scale, complex networks
- Skilled in leveraging threat intelligence and ML/DL techniques to analyze network traffic, detect malware operations, and identify suspicious activities such as connections to malware servers
- Experience with Explainable AI (XAI): knowledge of XAI techniques and tools (e.g., SHAP, LIME, Captum) to interpret and explain predictions of AI models
- Proven ability to design and implement models for anomaly detection using unsupervised learning techniques, such as clustering, autoencoders, and dimensionality reduction, to identify unusual patterns or outliers in large-scale datasets, crucial for detecting unknown threats or emerging malware behaviors
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
FR, PL + 2 more
