Senior ML Systems Engineer Production AI & Dist. Training

Ladders; United States; On-site; USD 270,000 - 310,000; Full time

Job summary

Ladders is seeking a Senior Research Engineer to advance large-scale ML systems in a remote US-based role. You will drive improvements across data quality, experimentation, and inference optimization, partnering with research, engineering, and product teams to scale production AI workloads.

You will contribute to state-of-the-art ML infrastructure, focusing on speed, reliability, and measurable business impact for research and production use cases.

Qualifications

• Expert proficiency in JAX/TPUs with Flax and Optax.
• Experience across the full ML pipeline from data to inference.
• Experience with large-scale distributed training and ML infrastructure.
• Ability to optimize production inference for large language and speech models.
• Ability to quantify improvements with well-defined metrics.

Responsibilities

• Improve experimental velocity by optimizing job launches and data accuracy.
• Maintain and enhance the JAX training framework for efficient TPU distributed training.
• Investigate and resolve quality issues in model data to drive measurable accuracy improvements.
• Build evaluation harnesses to analyze production model accuracy with a customer focus.
• Transform research prototypes into robust production systems with modernized architectures.
• Optimize production inference for speech language models through advanced techniques.
• Identify and eliminate performance bottlenecks across all system layers.

Skills

Python programming

Distributed ML

Experimentation

Tools

JAX

TPUs

Flax

Optax

Python

C++

Rust

Quantization

Continuous batching

Job description

Ladders is seeking a Senior Research Engineer to advance large-scale ML systems in a remote US-based role. You will drive improvements across data quality, experimentation, and inference optimization, partnering with research, engineering, and product teams to scale production AI workloads.

You will contribute to state-of-the-art ML infrastructure, focusing on speed, reliability, and measurable business impact for research and production use cases.