Machine Learning Engineer, AI Inference Solutions – Early Career

Jobtailor; Sunnyvale (CA); On-site; USD 110,000 - 160,000; Full time

Job summary

Jobtailor in Sunnyvale, CA is seeking a software engineer intern to contribute production code across the ML deployment platform, model-optimization workflows, and benchmarking infrastructure.

You will pair with senior engineers on deployment workflows, performance investigations, and tool development, building validators and analyzers while learning secure coding and safety practices for autonomous-driving software.

Qualifications

• Bachelor’s or Master’s degree in CS, ECE, or related field; degree completed before start date.
• Strong CS fundamentals in data structures, algorithms, OS, and computer architecture.
• Solid Python and/or C++ coding skills from coursework, internships, or projects.
• Hands-on AI/ML experience via classes, research, internships, or personal projects.
• Depth in at least one area: computer architecture, OS, distributed systems, or compilers.
• Software-engineering experience via internships, coursework, open-source, or competitions.
• Experience with coding assistants/agents like Cursor, Claude Code, or GitHub Copilot.
• Familiarity with ML systems stacks: PyTorch, torch.compile, TensorRT, ONNX, Triton, vLLM.
• Exposure to model optimization or GPU profiling tools.
• Familiarity with Airflow, Temporal, Flyte, Ray, Kubeflow.
• Experience building agentic or LLM-powered tools/workflows.
• Open-source contributions related to PyTorch, TensorRT, vLLM, OpenAI Triton, etc.
• Coursework, projects or publications touching ML systems.
• Familiarity with C++ and Linux development.

Responsibilities

• Contribute production code across the ML deployment platform, model-optimization workflows, and inference benchmarking/profiling infra.
• Pair with senior engineers on deployment workflows, performance investigations, model-optimization experiments, and platform tooling.
• Build, test, and maintain platform tools such as validators, performance probes, parity and sensitivity analyzers, and agentic tools.
• Investigate and help root-cause production deployment or performance issues involving compiler, kernel, runtime, and parity bugs.
• Collaborate with kernels, compiler, reduced-precision, parity, and model-development teams to plan model deployments to the AV stack.
• Participate in code reviews, design discussions, and technical documentation.
• Learn and follow secure coding, safety, and compliance practices for on-vehicle autonomous-driving software.

Skills

Python Programming

C++ Programming

AI/ML Experience

Model Optimization

Collaboration Skills

Data Structures

Algorithms

Operating Systems

Computer Architecture

Distributed Systems

Compilers

GPU Programming

Inference Optimization

Education

Bachelor’s or Master’s degree in CS, ECE, or related field

Tools

PyTorch

TensorRT

ONNX

Triton Inference Server

Cursor

Claude Code

GitHub Copilot

Airflow

Temporal

Kubeflow

Job description

• Contribute production code across the ML deployment platform, model-optimization workflows, and inference benchmarking/profiling infrastructure
• Pair with senior engineers on deployment workflows, performance investigations, model-optimization experiments, and platform tooling
• Build, test, and maintain platform tools such as validators, performance probes, parity and sensitivity analyzers, and agentic specialists
• Investigate and help root-cause production deployment or performance issues involving compiler, kernel, runtime, and parity bugs
• Collaborate with kernels, compiler, reduced-precision, parity, and model-development teams to plan and execute model deployments to the AV stack
• Participate in code reviews, design discussions, and technical documentation
• Learn and follow secure coding, safety, and compliance practices for on-vehicle autonomous-driving software

Requirements

• Recently completed or completing a Bachelor’s or Master’s degree by Spring 2026 in Computer Science, ECE, or a related technical field; degree must be completed before start date
• Strong computer science fundamentals in data structures, algorithms, operating systems, and computer architecture
• Solid coding skills in Python and/or C++, demonstrated through coursework, internships, or substantial projects
• Hands-on AI/ML experience through classes, research, internships, or personal projects
• Depth in at least one of computer architecture, operating systems, distributed systems, or compilers
• Demonstrated software-engineering experience through internships, coursework, open-source, research code, or competitions
• Experience with—or strong interest in—coding assistants/agents such as Cursor, Claude Code, or GitHub Copilot
• Ability to work effectively in collaborative, cross-functional teams and communicate clearly in writing and verbally
• Preferred: internship, research, or advanced coursework in ML systems, ML compilers, GPU programming, inference optimization, or distributed training/serving infrastructure
• Preferred: familiarity with PyTorch and modern ML compiler/runtime stacks such as torch.compile, TensorRT, ONNX, Triton Inference Server, or vLLM
• Preferred: exposure to model optimization or GPU profiling tools
• Preferred: familiarity with Airflow, Temporal, Flyte, Ray, or Kubeflow
• Preferred: experience building agentic or LLM-powered tools or workflows
• Preferred: open-source contributions related to PyTorch, TensorRT, vLLM, OpenAI Triton, or similar projects
• Preferred: coursework, projects, or publications touching ML systems
• Preferred: familiarity with C++ and Linux development

Core Competencies

Demonstrates strong coding skills in Python and C++, with hands-on experience in AI/ML and a solid understanding of computer science fundamentals. Capable of collaborating effectively in cross-functional teams while adhering to secure coding and compliance practices for autonomous-driving software.

Highest-signal resume keywords

• Python Programming
• C++ Programming
• AI/ML Experience
• Model Optimization
• Collaboration Skills

Hard Skills

• Data Structures
• Algorithms
• Operating Systems
• Computer Architecture
• Software Engineering
• Distributed Systems
• Compilers
• Performance Optimization
• GPU Programming
• Inference Optimization

Soft Skills

• Effective Communication
• Team Collaboration

Industry Keywords

• ML Deployment
• Model Development
• Performance Benchmarking
• Secure Coding Practices
• Autonomous Driving Software

Tools & Technologies

• PyTorch
• TensorRT
• ONNX
• Triton Inference Server
• Cursor
• Claude Code
• GitHub Copilot
• Airflow
• Temporal
• Kubeflow