Job Description: AI/ML Engineer
SecPod is a cybersecurity technology company based in India and the USA. Founded in 2008, SecPod (Security Podium, incarnated as SecPod) builds products and technologies focused on the
prevention of cyberattacks
. Our flagship platform,
SanerNow and SanerCloud
, is a state-of-the-art Cyber Hygiene solution that provides continuous, automated, and advanced vulnerability management for IT infrastructure.
We are looking for a skilled
AI/ML Engineer
to enhance our cybersecurity products with the power of Artificial Intelligence and Machine Learning. The ideal candidate will be responsible for developing and integrating AI/ML models, including classical ML, deep learning, and LLM-based solutions, to strengthen threat detection, risk analysis, and automation capabilities within SecPod products.
Responsibilities:
AI/ML Model Development
: Design and develop classical ML and deep learning models to predict, detect, and prevent cyber threats. Apply models to real-world cybersecurity datasets.
ML Fundamentals
: Implement supervised, unsupervised, and semi-supervised learning techniques such as regression, classification, clustering, anomaly detection, and ensemble methods.
LLM Fine-Tuning & RAG Architecture
: Fine-tune Large Language Models (LLMs) and build RAG (Retrieval-Augmented Generation) pipelines for tasks such as threat summarization, document understanding, and contextual search.
Vector Database Integration
: Work with vector databases (FAISS, Pinecone, Weaviate, etc.) to build high-performance semantic search solutions.
Data Analysis & Feature Engineering
: Analyze cybersecurity logs, vulnerability reports, and event data to engineer features and extract intelligence using statistical and ML techniques.
Model Lifecycle Management
: Handle the full ML lifecycle from data preprocessing and model training to evaluation, deployment, monitoring, and continuous improvement.
Model Optimization
: Improve model performance with techniques like hyperparameter tuning, cross-validation, transfer learning, and quantization (e.g., QLoRA).
Collaboration
: Work closely with cybersecurity analysts, software engineers, and the R&D team to embed ML and LLM-based solutions into SanerNow’s workflows.
Research and Innovation
: Stay updated with the latest trends in AI, ML, LLMs, cybersecurity, and threat intelligence. Experiment with new tools and techniques to drive innovation.
Documentation
: Prepare detailed technical documentation and present findings and model behaviors to cross-functional teams.
Qualifications:
Bachelor's or Master's degree in computer science, Data Science or a related field.
Strong understanding of
Transformers
and
core ML concepts
and algorithms (e.g., boosting models, decision trees, SVM, KNN, clustering, dimensionality reduction).
Proficiency in Python and ML libraries/frameworks like Scikit-learn, TensorFlow, PyTorch, Hugging Face Transformers, etc.
Practical experience in fine-tuning LLMs and working with embedding models (e.g., Sentence-BERT, OpenAI, Cohere).
Experience building RAG architectures and working with vector databases.
Knowledge of data preprocessing, EDA, model evaluation metrics, and deployment best practices.
Familiarity with cybersecurity domain concepts, tools, and real-world threat detection workflows is a strong advantage.
Experience with MLOps tools (e.g., MLflow, DVC, Docker, FastAPI) is a plus.
Excellent analytical, problem-solving, and communication skills.
Experience
:
0-2 Years (Data Science and AI/ML)]
