All jobs → Partner boards

Sr. ML Engineer, Network Intelligence

Tesla • Fremont, CA, US • published 2026-09-25 15:51:32.190139

Description

**What to Expect** You'll own the AI system behind an internal platform that investigates infrastructure problems using real\-time telemetry, metrics, and logs from thousands of devices. This isn't a chatbot wrapper or an API integration. You run the models on our own GPUs: serving, fine\-tuning, evaluating, and pushing them to work reliably in production. You'll be an early member of a small team where you make the architecture calls and ship to real users. When something breaks in the network, your system is what engineers turn to for answers. **What You'll Do*** Get LLM inference fast and reliable in production. Quantization, tensor parallelism, batching, KV cache tuning, speculative decoding and figuring out why the GPU is only hitting 3 tok/s when it should do 18 * Build the agent loop, the system where the model calls tools, gathers data from monitoring systems step by step, pieces together what happened, and writes a diagnostic report. Handle the messy parts: retries, timeouts, dedup, context limits * Build investigation tools that the agent calls: structured playbooks that query metrics databases, search logs, check alerts, and apply domain specific checks (threshold compar...

Get jobs like this daily in Telegram: @careeri_bot