Lead Developer Advocate

Parasail • San Mateo, CA

2d

About The Position

Parasail is seeking its first developer advocate to serve as its technical voice on inference, covering open-weight models, the hardware they run on, and the applications built on top. The role involves conducting original experiments on inference in production, sharing findings through technical writing and public speaking, and working closely with performance and platform engineers. The advocate will also represent Parasail with the model labs and hardware partners it works with. The role begins as an individual contributor, with the opportunity to build and lead a team as the function grows.

Parasail is a multi-silicon inference cloud that matches workloads to hardware including NVIDIA, AMD, Positron, and other next-generation accelerators, tunes underlying kernels, and evaluates performance across trillions of tokens a day. The company is headquartered in San Mateo, California, and is backed by Kindred Ventures, Turing Capital, Basis Set, and others.

Requirements

• Experience doing technical work in public, such as conference talks or writing that engineers cite; relevant backgrounds may include developer advocacy, ML education, research, or engineering.
• Ability to build with LLMs in Python.
• Ability to read serving engine code.
• Ability to explain GPU-level tradeoffs behind latency, throughput, and cost.
• Ability to communicate complex systems ideas clearly in writing and on stage without oversimplifying them.
• Contributed to or maintained open-source software used by developers.
• Knowledge of people across the AI ecosystem, or ability to build those connections quickly.
• Comfort building a function without an established playbook.

Nice To Haves

• Experience with vLLM or SGLang, or with accelerators beyond NVIDIA.
• Published evaluations or benchmark methodology for LLM systems.
• Accepted talks at major AI, ML, or systems conferences.
• A following on X, LinkedIn, or another platform earned through technical work.
• A research or teaching background in ML or systems.

Responsibilities

• Conduct original technical work on how inference behaves in production, including serving engines, hardware, latency, cost, and quality.
• Publish in-depth technical articles and reference materials for engineers, and share work on X, LinkedIn, Hacker News, and Parasail's own channels.
• Prepare conference proposals and give talks at conferences and meetups for AI engineers, infrastructure teams, and model builders.
• Lead developer workshops and participate in podcasts and panels.
• Launch new models with open-weight model labs.
• Demonstrate the capabilities of new silicon with hardware partners such as AMD, Positron, and d-Matrix.
• Build integrations with frameworks and tools developers already use.
• Coordinate with model labs and hardware partners on benchmarking and develop joint benchmarks.
• Work with Parasail's performance and platform engineers.
• Establish the developer advocacy function and, as it grows, build and lead a team.

Benefits

• Competitive base salary and meaningful equity.
• Comprehensive health, dental, and vision coverage.
• Generous paid time off and company holidays.
• 401(k).
• Family planning and fertility benefits.
• Access to Parasail's multi-silicon hardware fleet for experiments.

What This Job Offers

• Job Type: Full-time
• Career Level: Senior
• Education Level: No Education Listed