Senior Machine Learning Engineer

Bulgaria·Bulgariasenior

Machine Learning EngineerData

0 views0 saves0 applied

Apply Now

Quick Summary

Overview

Key Responsibilities

Build the ML stack from the ground up - Design and implement the data pipelines, feature extraction, model training, and serving infrastructure needed for production-grade anomaly detection.

Technical Tools

etlmachine-learning

Since 2016, Wallarm has been on a mission to secure the internet's critical infrastructure: APIs. Today, we are the trusted choice for over 200 of the world's most innovative companies, from high-growth startups to Fortune 500 and Nasdaq leaders. Our unified platform provides full-lifecycle API security — helping teams discover their attack surface, protect against modern threats, and respond to incidents in real-time. As a graduate of Y Combinator and fueled by a recent $55M Series C, we are scaling our global, remote-first team of 150+ innovators to solve the next generation of security challenges.

We're building ML-powered detection systems that protect APIs from automated abuse credential stuffing, scraping, enumeration, and attack patterns that evolve daily. This is a greenfield effort: we have the data and the ideas, but the ML infrastructure, pipelines, and models need to be built from scratch.

You'll be the first dedicated ML engineer on the team, working closely with engineers, security researchers and DevOps. This is a senior IC role with a clear path to technical leadership - we plan to grow the ML function around this hire.

Responsibilities

~1 min read

→
Build the ML stack from the ground up - Design and implement the data pipelines, feature extraction, model training, and serving infrastructure needed for production-grade anomaly detection.
→
Detecting anomalies in API traffic - Your first major outcome: build a system that identifies malicious behavioral patterns across client sessions with high precision and recall, trained per-client.
→
Own the full lifecycle - From raw data exploration and feature engineering through model development, evaluation, deployment, and continuous monitoring. No handoffs to a separate "productionization" team.
→
Design experiments and metrics - Build offline evaluations, define detection-quality metrics, and monitor for false positives, drift, and adversarial adaptation.
→
Work with text and structured behavioral data - Extract signals from API sessions, request sequences, payloads, and traffic metadata using NLP and statistical techniques.
→
Leverage LLMs where they add value - Explore embedding-based models and LLM-augmented approaches for signal enrichment, classification, and explainability.
→
Shape the technical direction - Document findings, present to cross-functional teams, and help define the ML roadmap as the team grows.