Staff Machine Learning Engineer (ML Infrastructure)

TL;DR

Staff Machine Learning Engineer (ML Infrastructure): Designing and operating high-scale ML infrastructure for home security products with an accent on real-time computer vision inference and LLM/GenAI serving. Focus on optimizing Kubernetes-based platforms using Ray, reducing deployment friction, and scaling GPU utilization for production workloads.

Location: Hybrid in Boston, MA (office attendance required on two core days)

Salary: $183,500–$269,100 per year

Company

A high-tech home security company focused on keeping every home secure through innovation and a collaborative, no-ego culture.

What you will do

• Drive architecture decisions for a Kubernetes-based ML platform using Ray, KServe, Triton, and vLLM across real-time and batch workloads.
• Design and evolve cloud-side inference systems that process live video and events from security devices in real time.
• Establish LLM/GenAI serving infrastructure, including model serving patterns, KV-cache, and evaluation pipelines.
• Mentor engineers through design and code reviews to elevate the technical bar across the Cloud ML team.
• Define SLOs and observability standards while leading incident response and postmortems for critical ML systems.

Requirements

• 8+ years of software/ML engineering experience with a track record of operating production ML systems at scale.
• Deep expertise in cloud ML infrastructure on Kubernetes, specifically with hands-on production experience with Ray.
• Strong production experience with AWS (EKS, S3, IAM) and Kafka.
• Proven ability to design high-throughput, low-latency inference systems with GPU-aware scheduling and autoscaling.
• Proficiency in Python and strong staff-level technical leadership capabilities.
• Must be based in Boston, MA to support the hybrid work model.

Nice to have

• Hands-on production experience with LLM serving (vLLM, TGI, TensorRT-LLM, SGLang).
• Experience with real-time video or streaming ML pipelines (Kafka, Kinesis, Flink).
• Background in production CV workloads, model formats, and GPU/accelerator tradeoffs.
• Experience with model lifecycle tooling such as MLflow or Weights & Biases.
• Open source contributions to the ML infrastructure ecosystem.

Culture & Benefits

• Hybrid work model allowing teams to split time between a state-of-the-art office and home.
• Comprehensive total rewards package including medical, retirement, and lifestyle benefits.
• Annual bonus program and equity participation.
• Free hirify.global system and professional monitoring for your home.
• Inclusive environment with Employee Resource Groups (ERGs) for networking and mentorship.