Senior AI Platform Engineer (Generative AI)

**Senior AI Platform Engineer (Generative AI)

Boston, MA (Hybrid preferred/open to remote)

12 Month + contract (or contract to hire, if desired)**

We are looking for a senior AI Platform Engineer to build, operate, and scale generative AI systems in production. This role sits at the intersection of ML systems, platform engineering, and SRE, supporting large-scale inference workloads in regulated, enterprise environments.

This is not a research-only role — candidates must have real production experience supporting AI systems end-to-end.

Core Responsibilities

• Design, deploy, and operate production-grade generative AI platforms
• Serve and scale large language models using modern inference frameworks (e.g., vLLM, SGLang, TensorRT-LLM)
• Own platform reliability, including on-call responsibilities, incident response, and performance tuning
• Build and operate Kubernetes-based infrastructure for AI workloads
• Partner with application teams consuming the AI platform and support production use cases
• Evaluate and integrate developer productivity tools (Copilot agents, Cursor, etc.) responsibly

Required Experience

• 5+ years of professional software engineering experience
• Hands-on experience in AI/ML systems (not just API consumption)
• Proven experience operating production platforms with:
• Kubernetes
• Cloud infrastructure (AWS, GCP, or Azure)
• Monitoring, alerting, and incident response
• Prior experience with platform engineering or SRE concepts
• Strong fundamentals in algorithms, systems design, and debugging

Strongly Preferred

• Experience serving LLMs at scale using raw or managed GPUs
• Familiarity with inference optimization and cost-performance tradeoffs
• Background in:
• Large tech companies
• Research labs or higher-ed research environments
• Enterprise platforms with strict reliability requirements
• Daily, practical use of GenAI developer tools (Copilot, Cursor, Windsurf, etc.)

What Success Looks Like

• You can reason about model serving, infrastructure, and failure modes, not just model outputs
• You are comfortable being on-call for systems you build
• You understand when to use AI tools — and when not to
• You can support teams consuming AI platforms without hand-holding

What This Role Is
*Not*

• Not a junior ML role
• Not a pure research position
• Not a “prompt engineer” role
• Not a platform consumer-only position