ML Inference Engineer â Terminal-Bench Task Designer (vLLM / SGLang / TensorRT-LLM)
Toptal · vía remoteok · Senior
🇦🇷 Sí, aplica para Argentina
Aviso dice 'Anywhere in the World' sin restricciones geográficas ni de residencia. Toptal contrata talent global.
✦ Resumen en castellano
Toptal busca ingenieros ML para diseñar desafíos (tasks) de benchmark de terminal que simulen trabajo real de inferencia y serving de modelos. El rol es 100% remoto, por tareas: diseñás un challenge basado en tu experiencia, escribís la solución de referencia, armás las validaciones automáticas y lo empaquetás en Docker. Necesitás 3+ años hands-on en ML inference (vLLM, SGLang, TensorRT-LLM), experiencia con PyTorch/JAX, Python, CLI y capacidad de explicar cómo fallan silenciosamente los modelos. Se paga por task completada (60–75 minutos cada una); no hay salario fijo estructurado.
Aviso original en remoteok
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 tas…
Ver y postularte en remoteok →La descripción completa y la postulación viven en la fuente. Nuestro valor está en el análisis de arriba.