Required Senior ML Research Engineer
Israel: Tel Aviv/ Hybrid
R&D | Full Time | Job Id: 24793
Your Impact & Responsibilities:
As a Senior ML Research Engineer, you will be responsible for the end-to-end lifecycle of large language models: from data definition and curation, through training and evaluation, to providing robust models that can be consumed by product and platform teams.
Own training and fine-tuning of LLMs / seq2seq models: Design and execute training pipelines for transformer-based models (encoder-decoder, decoder-only, retrievalaugmented, etc.), and fine-tune open-source LLMs -specific data (security content, logs, incidents, customer interactions).
Apply advanced LLM training techniques such as instruction tuning, preference / contrastive learning, LoRA / PEFT, continual pre-training, and domain adaptation where appropriate.
Work deeply with data: define data strategies with product, research and domain experts; build and maintain data pipelines for collecting, cleaning, de-duplicating and labeling large-scale text, code and semi-structured data; and design synthetic data generation and augmentation pipelines.
Build robust evaluation and experimentation frameworks: define offline metrics for LLM quality (task-specific accuracy, calibration, hallucination rate, safety, latency and cost); implement automated evaluation suites (benchmarks, regression tests, redteaming scenarios); and track model performance over time.
Scale training and inference: use distributed training frameworks (e.g. DeepSpeed, FSDP, tensor/pipeline parallelism) to efficiently train models on multi-GPU / multi-node clusters, and optimize inference performance and cost with techniques such as quantization, distillation and caching.
Collaborate closely with security researchers and data engineers to turn domain knowledge and threat intelligence into high-value training and evaluation data, and to expose your models through well-defined interfaces to downstream product and platform teams.
Requirements: 5+ years of hands-on work in machine learning / deep learning, including 3+ years focused on NLP / language models.
Proven track record of training and fine-tuning transformer-based models (BERT-style, encoder-decoder, or LLMs), not just consuming hosted APIs.
Strong programming skills in Python and at least one major deep learning framework (PyTorch preferred; TensorFlow).
Solid understanding of transformer architectures, attention mechanisms, tokenization, positional encodings, and modern training techniques.
Experience building data pipelines and tools for large-scale text / log / code processing (e.g. Spark, Beam, Dask, or equivalent frameworks).
Practical experience with ML infrastructure, such as experiment tracking (Weights & Biases, MLflow or similar), job orchestration (Airflow, Argo, Kubeflow, SageMaker, etc.), and distributed training on multi-GPU systems.
Strong software engineering practices: version control, code review, testing, CI/CD, and documentation.
Ability to own research and engineering projects end-to-end: from idea, through prototype and controlled experiments, to models ready for integration by product and platform teams.
Good communication skills and the ability to work closely with non-ML stakeholders (security experts, product managers, engineers).
Nice to have:
Experience with RLHF / preference optimization, safety alignment, or other humanfeedback-in-the-loop approaches to training LLMs.
Experience with retrieval-augmented generation (RAG), dense retrieval, vector databases, and embedding training.
Background in security / cyber domains such as threat detection, malware analysis, logs, or SOC tools.
Experience with multilingual models (e.g., Hebrew + English) and cross-lingual training.
Experience in a product environment where models must meet reliability, scale, and cost constraints.
This position is open to all candidates.