# AI Inference Engineer - Model Optimization & Deployment

**Company:** [Zoox](https://hotfix.jobs/companies/zoox)
**Location:** Foster City, CA, San Diego, CA, Seattle, WA
**Role:** ML Engineering
**Salary:** $242k – $290k/yr
**Skills:** TensorRT, Tensorrt-Llm, CUDA, PyTorch, C++, Python, Ptq, Qat, Lora, Qlora, Flashattention, Pagedattention, Deepspeed, Ray
**Posted:** 2026-04-11

> Optimizes and deploys large-scale AI models (LLMs, VLMs) for real-time inference on power-constrained vehicle hardware. Requires expertise in quantization, TensorRT compilation, custom CUDA kernels, and production C++/Python for edge devices.

## Job Description

## Responsibilities
- Optimize large-scale models (LLMs, VLMs) using advanced quantization (PTQ, QAT), mixed-precision inference workflows, and parameter-efficient fine-tuning (LoRA, QLoRA).
- Architect and implement model conversion and compilation pipelines using **TensorRT** and **TensorRT-LLM** for edge deployment.
- Perform rigorous parity checking, accuracy recovery, and latency benchmarking between **PyTorch** frameworks and compiled edge binaries.
- Write and optimize custom **CUDA** kernels and **TensorRT** Plugins to maximize memory bandwidth and minimize latency on AI accelerators.
- Write production-level, highly concurrent, and memory-safe **C++** and **Python** code for real-time inference on vehicle SOCs.

## Qualifications
- Deep expertise in model quantization (**PTQ**, **QAT**) and mixed-precision inference workflows (**INT8**, **FP8**, **INT4**, **BF16/FP16**).
- Proven experience optimizing large-scale models (**LLMs**, **VLMs**, or **VLAs**) utilizing **KV-cache** optimization (e.g., **PagedAttention**), **Speculative Decoding**, and Efficient Attention mechanisms (**FlashAttention**, **Linear Attention**).
- Extensive experience with model conversion/compilation pipelines (**TensorRT**, **TensorRT-LLM**) and performing rigorous parity/latency benchmarking.
- Proficiency in low-level programming for AI accelerators, specifically writing and optimizing custom **CUDA** kernels and **TensorRT** Plugins.
- Production-level **C++** (14/17/20) and **Python** programming skills, with experience writing concurrent, memory-safe, real-time inference code for edge devices.

## Bonus Qualifications
- Experience with distributed training pipelines and model/tensor parallelism (**PyTorch Distributed**, **Ray**, **DeepSpeed**, **Megatron-LM**) and runtime efficiency optimization for GPU clusters.
- Familiarity with autonomous driving perception stacks (temporal 3D object detection, **BEV**, 3D Occupancy Networks) and processing multi-modal sensor streams (**Vision**, **LiDAR**, **Radar**).
- Understanding of end-to-end autonomous driving paradigms (**VLA** models, closed-loop simulation validation).

## Similar roles

- [Clinician Scientist](https://hotfix.jobs/jobs/ced7dbd8-cebc-4b65-878e-bbfdc8c8f995) - Abridge - San Francisco, CA - $236k – $277k/yr
- [Researcher, Alignment Oversight](https://hotfix.jobs/jobs/38516bf4-430f-4588-bcd3-f148cc262645) - OpenAI - San Francisco, CA - $250k – $445k/yr
- [Research Scientist / Engineer — Multimodal Agent](https://hotfix.jobs/jobs/c336622c-2837-473e-b233-d1aae1a465c3) - Luma AI - Palo Alto, CA - $250k – $450k/yr
- [Research Engineer, Evals](https://hotfix.jobs/jobs/b26f895d-8d3e-45a8-8acd-55835c2721d3) - Variance - San Francisco, CA - $250k – $400k/yr
- [Research Engineer, Judgment Systems](https://hotfix.jobs/jobs/d22f5c9e-5811-409f-8801-81a01c43869a) - Variance - San Francisco, CA - $250k – $400k/yr

**Apply:** https://hotfix.jobs/jobs/98f84382-a376-49eb-ab15-fc95bdd56e3f
**Canonical:** https://hotfix.jobs/jobs/98f84382-a376-49eb-ab15-fc95bdd56e3f