Machine Learning Infrastructure Engineer

TRM Labs

About The Position

TRM Labs provides blockchain analytics and AI solutions to help law enforcement and national security agencies, financial institutions, and cryptocurrency businesses detect, investigate, and disrupt crypto-related fraud and financial crime. TRM’s blockchain intelligence and AI platforms include solutions to trace the source and destination of funds, identify illicit activity, build cases, and construct an operating picture of threats. TRM is trusted by leading agencies and businesses worldwide who rely on TRM to enable a safer, more secure world for all. TRM Labs provides blockchain analytics and AI solutions to help law enforcement and national security agencies, financial institutions, and cryptocurrency businesses detect, investigate, and disrupt crypto-related fraud and financial crime. TRM’s blockchain intelligence and AI platforms include solutions to trace the source and destination of funds, identify illicit activity, build cases, and construct an operating picture of threats. TRM is trusted by leading agencies and businesses worldwide who rely on TRM to enable a safer, more secure world for all. At TRM, we’re on a mission to build a safer financial system for billions of people around the world. Our next-generation platform, which combines threat intelligence with machine learning, enables financial institutions and governments to detect cryptocurrency fraud and financial crime at an unprecedented scale. As a Senior Software Engineer, ML Infrastructure at TRM Labs, you will collaborate with data scientists, engineers, and product managers to design and operate scalable GPU-backed infrastructure that powers TRM’s AI systems. You will work at the intersection of distributed systems, cloud infrastructure, GPU performance engineering, and applied machine learning — building the foundation that enables high-throughput, production-grade ML workloads.

Requirements

Bachelor’s degree (or equivalent) in Computer Science or related field.
5+ years of experience building and operating distributed systems or infrastructure in production environments.
Experience deploying and operating ML/LLM inference workloads on GPU clusters in cloud environments (AWS and/or GCP).
Deep understanding of high-throughput inference systems, including batching strategies, token throughput optimization, and the trade-offs between latency, throughput, and cost.
Experience with one or more ML serving frameworks such as Triton Inference Server, vLLM, Ray Serve, ONNX Runtime, or HuggingFace Optimum.
Experience optimizing GPU load, memory efficiency, and performance bottlenecks in production systems.
Familiarity with distributed inference strategies including model parallelism and tensor parallelism.
Experience working with Kubernetes or equivalent orchestration systems in cloud environments.
Adaptable. Goals can change fast. You anticipate and react quickly.
Autonomous. You own what you work on. You move fast and get things done.
Excellent communication. You communicate complex ideas effectively to both technical and non-technical audiences, verbally and in writing.
Collaborative. You work effectively in a cross-functional team and with people at all levels in an organization.

Nice To Haves

Familiarity with heterogeneous accelerators (e.g., Inferentia) is a plus.
CUDA familiarity and experience debugging GPU-related issues is a plus.

Responsibilities

Design and operate GPU cluster infrastructure.
Build and manage GPU-backed environments in cloud settings, including orchestration, autoscaling, resource isolation, and workload management across multiple concurrent models and users.
Optimize high-throughput inference.
Implement and tune serving systems that maximize token throughput, batching efficiency, GPU occupancy, and cost effectiveness across interactive and batch workloads.
Enable distributed inference strategies.
Support and operationalize model parallelism, tensor parallelism, and other distributed serving patterns for large-scale models.
Implement model optimization and compilation workflows.
Integrate and optimize acceleration stacks such as TensorRT, ONNX Runtime, vLLM, FlashAttention, and related tooling to improve performance and reduce inference cost.
Schedule heterogeneous workloads.
Design systems that manage multiple models, multiple users, and mixed workload types across heterogeneous accelerators (e.g., NVIDIA GPUs, Inferentia), ensuring predictable performance under varying demand.
Build observability into ML infrastructure.
Instrument systems to measure GPU load, memory utilization, batching efficiency, queue depth, and token throughput, and use data to continuously improve performance and reliability.
Partner across engineering teams.
Work closely with infrastructure, ML, and product teams to ensure models transition smoothly from experimentation to production-grade, highly available services.