Strategic Overview
ML Inference Engineer â Terminal-Bench Task Designer (vLLM / SGLang / TensorRT-LLM) at Toptal is defined by the responsibilities and candidate requirements in the employer's listing.
The published role emphasizes work such as ⢠Design expert-level Terminal-Bench tasks that turn real, paid ML inference work from your own experience into challenges an AI agent must solve end to end.
The role is listed for Anywhere in the World with a remote working arrangement, giving candidates the practical context needed to assess fit before applying.
Key information at a glance
About This Role
Overview
We are building a benchmark that tests how well AI agents handle real expert work in a terminal. We are hiring ML inference and serving experts to turn real, paid tasks from their jobs into expert-level Terminal-Bench challenges. Each task includes the environment, a working solution, and an automated check that proves the result is correct.
***THIS IS A TASK BASED COMPENSATION MODEL. PLEASE CHECK THE APPLICATION QUESTIONS FOR MORE DETAILS.***
Key Responsibilities & Objectives
- ⢠Design expert-level Terminal-Bench tasks that turn real, paid ML inference work from your own experience into challenges an AI agent must solve end to end.
- ⢠Define the files, systems and environments each task runs on, such as model serving with streaming, so the challenge is realistic, reproducible and command-line solvable.
- ⢠Build automated checks that objectively prove a result is correct, including cases where ML outputs go wrong silently, such as numerical drift or metric bugs.
- ⢠Trained, served or evaluated models at real scale (multi-GPU or production serving), not only notebooks or API calls
- ⢠Task vetting instead of an interview: complete a vetting task so the client can assess your task design
Required Qualifications & Candidate Blueprint
- ⢠3+ years doing ML inference or serving work hands-on (not only studying, selling or managing it), or a PhD plus active research in the subfield
- ⢠Hands-on with PyTorch or JAX internals and serving stacks such as vLLM, SGLang or TensorRT-LLM
Salary & Benefits
The available source data does not publish a numerical salary range for this opening. We do not estimate or substitute third-party figures.
Full Job Description
The following is the complete job description supplied by the source. We sanitize unsafe markup and remove external links, but do not shorten or rewrite the employer's source content.
Overview
We are building a benchmark that tests how well AI agents handle real expert work in a terminal. We are hiring ML inference and serving experts to turn real, paid tasks from their jobs into expert-level Terminal-Bench challenges. Each task includes the environment, a working solution, and an automated check that proves the result is correct.
***THIS IS A TASK BASED COMPENSATION MODEL. PLEASE CHECK THE APPLICATION QUESTIONS FOR MORE DETAILS.***
Responsibilities
⢠Design expert-level Terminal-Bench tasks that turn real, paid ML inference work from your own experience into challenges an AI agent must solve end to end.
⢠Define the files, systems and environments each task runs on, such as model serving with streaming, so the challenge is realistic, reproducible and command-line solvable.
⢠Write a working reference solution for every task and verify it runs end to end, sized for about 60 to 75 minutes of expert effort.
⢠Build automated checks that objectively prove a result is correct, including cases where ML outputs go wrong silently, such as numerical drift or metric bugs.
⢠Package tasks with Docker and Git so they are reproducible, and document the systems, tools, data and rules involved so reviewers can validate difficulty.
⢠Iterate on tasks based on reviewer feedback and agent test runs, adjusting difficulty and fixing ambiguities so each task stays expert-level, fair and objectively gradable.
Skills/Experience
⢠3+ years doing ML inference or serving work hands-on (not only studying, selling or managing it), or a PhD plus active research in the subfield
⢠Did this work in the last 3 years and can name the systems, tools, data and rules used
⢠Trained, served or evaluated models at real scale (multi-GPU or production serving), not only notebooks or API calls
⢠Hands-on with PyTorch or JAX internals and serving stacks such as vLLM, SGLang or TensorRT-LLM
⢠Can explain how ML results go wrong without errors (numerical drift, metric bugs) and how to catch them
⢠Technical fluency in Python and the command line, and with files, CSV/JSON, APIs or databases
⢠Availability to start by early November 2026 and complete tasks of about 60 to 75 minutes each
Nice-to-have
⢠AI lab or LLM infrastructure experience
⢠Contributions to PyTorch, vLLM or SGLang
⢠GPU profiling experience
⢠Docker and Git proficiency
⢠Experience writing automated tests
Process
⢠Task vetting instead of an interview: complete a vetting task so the client can assess your task design
⢠Paid per task; each task takes about 60 to 75 minutes
⢠Work is delivered task by task, with reviewer feedback on submissions
⢠Expected start in early November 2026
Please mention the word **ASTONISHED** and tag RMmEwNjo5OGMwOjM2MDA6OjEwMw== when applying to show you read the job post completely (#RMmEwNjo5OGMwOjM2MDA6OjEwMw==). This is a beta feature to avoid spam applicants. Companies can search these words to find applicants that read this and see they're human.
Editor’s Market Perspective (Our Custom Analysis)
Why This Position Matters
This opening may suit candidates who can demonstrate experience relevant to the employer's published requirements. Its strongest career signal is the scope of the work itself — particularly ⢠Design expert-level Terminal-Bench tasks that turn real, paid ML inference work from your own experience into challenges an AI agent must solve end to end. — rather than a generic title alone.
Resume & Application Strategy
For the application, connect specific examples from your experience to the responsibilities and qualifications in the employer's description. Quantify outcomes from comparable work, and place the most relevant evidence near the top of the resume. When the employer explicitly names tools, platforms, leadership scope, or domain experience, use those source terms accurately and in context.
We organize source-provided information into this independent job-seeker overview. Compensation is shown only when the source provides it; the official listing remains the authority for current requirements and application instructions.