Machine Learning Infrastructure Engineer

Build a Safer World. TRM Labs provides blockchain analytics and AI solutions to help law enforcement, 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 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 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 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. The Impact You’ll Have Here 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. What We’re Looking For 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. Familiarity with heterogeneous accelerators (e.g., Inferentia) is a plus. CUDA familiarity and experience debugging GPU‑related issues is a plus. 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. Life at TRM We are building a safer world. That promise shows up in how we work every day. TRM runs fast. Really fast. We’re a high‑velocity, high‑ownership team that expects clarity, follow‑through, and impact. People who thrive here are energized by hard problems, experimentation, and direct feedback. If something takes months elsewhere, it often ships here in days. That pace isn’t for everyone. If you are optimizing primarily for consistent work‑life balance, use the interview process to pressure‑test fit. We want teammates who thrive here, not just survive here. AI Fluency at TRM AI fluency is a baseline expectation at TRM. We believe AI meaningfully changes how top performers operate. We expect every team member to use AI to accelerate and reimagine their craft, not just automate surface tasks. At TRM, AI Fluency Means You Are Among The Top 10 Percent Of Operators In Your Function In How You Apply AI To Accelerate repeatable workflows Structure and solve problems Improve output quality Increase speed and leverage You will be evaluated on applied AI fluency during the interview process. Leadership Principles Impact‑Oriented Trailblazer: We put customers first and move with speed, focus, and adaptability. We treat every plan like an experiment – test, ship, measure, and iterate quickly. Master Craftsperson: We care deeply about our craft. We balance speed with high standards, own outcomes end‑to‑end, and invest in getting better everyday. Inspiring Colleague: We add clarity and energy, not noise. We bring humility, candor, and a one‑team mindset — giving and receiving feedback to make the team stronger. The impact you will have Driving critical investigations that can’t wait for typical business hours. Shipping products in days when others would schedule quarters. Partnering with teams across time zones to deliver insights while the story is still unfolding. Building new solutions from first principles when the playbook doesn’t yet exist. Protecting victims and customers by tracing illicit activity and disrupting criminal networks. Join our Mission At TRM we care deeply about our craft. We are looking for individuals who want their work to matter, who experiment with speed and rigor, and who take pride in building a safer world for billions of people. If you’re excited by TRM’s mission but don’t check every box, we encourage you to apply — we hire for slope, judgment, and the will to learn fast. TRM is a Series C company with $220M in total funding, backed by Blockchain Capital, Goldman Sachs, Bessemer, Y Combinator, Thoma Bravo, and others. Headquartered in San Francisco, TRM operates as a distributed‑first company with hubs in Los Angeles, San Francisco, New York, Washington D.C., London, and Singapore. Privacy Policy And Additional Information By submitting your application, you are agreeing to allow TRM to process your personal information in accordance with the TRM Privacy Policy. Our typical hiring cycles for specialized roles span 24 to 36 months. Accordingly, we retain your personal information for up to 36 months to evaluate your application and to consider you for current and future employment opportunities, unless you request earlier deletion or a different retention period is required or permitted by law. To notify TRM Labs that you believe this job posting is non‑compliant, please submit a report through this form. No response will be provided to inquiries unrelated to job posting compliance. We are committed to providing reasonable accommodations to applicants with disabilities, and requests can be made via this form. Recruitment agencies TRM Labs does not accept unsolicited agency resumes. Please do not forward resumes to TRM employees. TRM Labs is not responsible for any fees related to unsolicited resumes and will not pay fees to any third‑party agency or company without a signed agreement. Learn More Company Values | Interviewing | FAQs #J-18808-Ljbffr