Senior ML Engineer

As an ML Engineer at Bold, you’ll build the AI inference layer that runs directly on customer endpoints. You will take small language model from prototype to efficient, reliable, production-ready implementations across hardware and software.

This role is for you if you want to be at the forefront of edge inference, turning ML into high-performance production systems that run under real-world constraints.

Key Responsibilities:

• Build and optimize the inference engine, utilizing CPU and GPU to run small language models on the edge.
• Develop the engineering components around model execution, including preprocessing, post-processing, telemetry, and failure handling.
• Optimize runtime performance across latency, CPU usage, memory footprint, startup time, binary size, and reliability constraints.
• Apply strong systems engineering judgment when balancing detection quality, performance, explainability, operational complexity, and maintainability.
• Own ambiguous technical problems end to end, from design and implementation through production rollout.

Qualifications:

• 5+ years of engineering experience, with strong hands-on experience in a systems language like Rust, C, or C++.
• Experience building production ML, classification, detection, or decisioning systems.
• Strong understanding of model inference, classification pipelines, runtime constraints, and performance optimization.
• Solid understanding of systems design, operating systems, multi-threading, async programming, and resource management.
• Good understanding of ML fundamentals, including model architectures, feature engineering, classifiers, embeddings, thresholds, and evaluation tradeoffs.
• Strong ownership, collaboration, and communication skills, with the ability to work effectively across disciplines.