Staff Software Engineer (ML Infrastructure)

TL;DR

Staff Software Engineer (ML Infrastructure): Building and scaling cloud-side ML infrastructure and applied ML research for intelligent home security products with an accent on real-time computer vision inference and LLM/GenAI serving. Focus on designing high-throughput, low-latency distributed systems, optimizing GPU utilization, and establishing model lifecycle management.

Location: Hybrid in Boston, MA (expectation to be in office 2 core days per week)

Salary: $146,600 – $215,100 per year

Company

A high-tech home security company dedicated to keeping every home secure through a culture of collaboration and innovation.

What you will do

• Drive architecture and technical direction for a Kubernetes-based ML platform using Ray, KServe, Triton, and vLLM.
• Design and evolve cloud-side real-time computer vision inference systems to process live video and events.
• Establish production infrastructure for LLM/GenAI serving, including KV-cache and batching strategies.
• Mentor engineers through design and code reviews and define best practices for model lifecycle management.
• Lead incident response and define SLOs and observability standards for critical ML services.

Requirements

• 8+ years of software engineering experience with a track record of building large-scale distributed systems.
• Deep expertise in high-throughput, low-latency services and operational experience running them at scale.
• Strong production experience with Kubernetes, AWS (EKS, S3, IAM), Kafka, and CI/CD.
• Proficiency in Python; experience with Go, C++, or Rust is a plus.
• Staff-level technical leadership skills to drive ambiguous, cross-cutting initiatives.
• Must be based in or able to work hybrid in Boston, MA.

Nice to have

• Hands-on experience with Ray, KServe, Triton, or vLLM serving stacks.
• Experience with LLM serving in production (TensorRT-LLM, SGLang, etc.).
• Experience building real-time video or streaming pipelines using Kafka, Kinesis, or Flink.
• Expertise in GPU-based inference systems and GPU-aware scheduling.
• Familiarity with ML lifecycle tooling such as MLflow or Weights & Biases.

Culture & Benefits

• Mission-driven, inclusive, and "no ego" collaborative work environment.
• Comprehensive total rewards package including medical, retirement, and lifestyle benefits.
• Free hirify.global system and professional monitoring for your home.
• Hybrid work model providing a balance between office collaboration and home flexibility.
• Employee Resource Groups (ERGs) for networking and professional advocacy.