Forward Deployed Engineer

About Novita AI

Novita AI is an AI & Agent Cloud platform for builders.

We provide a unified platform for Model APIs, GPU Cloud, and Agent Sandbox infrastructure, helping developers and enterprises build, deploy, and scale production AI systems without managing complex infrastructure. Today, thousands of teams rely on Novita to power AI agents, coding tools, multimodal applications, and large-scale inference workloads.

As a Forward Deployed Engineer (FDE), you’ll work at the intersection of engineering, customer success, and product. You’ll partner closely with customers to understand their AI workloads, deploy solutions, troubleshoot production issues, and influence the evolution of our platform.

You will act as an extension of our customers’ engineering teams, helping them integrate model APIs, GPU infrastructure, and sandbox environments into real-world applications.

This role is ideal for someone who enjoys wearing multiple hats—software engineer, solutions architect, product thinker, and trusted technical advisor.

• Work directly with customers to understand their AI products, technical requirements, and business goals.

• Deploy and integrate Novita AI products, including:

  • Model APIs and inference endpoints

  • Dedicated model hosting

  • GPU cloud infrastructure

  • Agent sandbox environments

• Debug production issues across APIs, networking, containers, GPUs, and distributed systems.

• Build customer-specific solutions, integrations, demos, and prototypes.

• Travel to customer sites when necessary and collaborate closely with their engineering teams.

• Translate customer feedback into product requirements and work with internal engineering teams to improve our platform.

• Create reusable tooling, automation, and reference implementations that benefit future customers.

• Support proof-of-concepts (PoCs) and help customers successfully move into production.

• Strong software engineering fundamentals.

• Proficiency in Python and at least one additional programming language.

• Experience building or deploying cloud-native applications.

• Familiarity with Docker, Kubernetes, Linux, and networking concepts.

• Strong debugging and problem-solving skills in production environments.

• Excellent communication skills and ability to work directly with customers.

• Ability to operate with ambiguity and move quickly in a startup environment.

• Experience with AI/ML infrastructure, LLMs, or inference systems.

• Familiarity with vLLM, SGLang, Ray, or distributed serving frameworks.

• Experience working with GPUs, CUDA, or large-scale compute systems.

• Background in solutions engineering, developer relations, or customer-facing engineering roles.

• Experience building AI agents, coding agents, or sandboxed execution environments.

• Prior startup experience or experience as an early engineer.

• Professional working proficiency in Mandarin Chinese.

In your first six months, you will:

• Help multiple customers successfully launch AI workloads into production.

• Become a trusted technical advisor for strategic accounts.

• Build reusable solutions that accelerate future customer deployments.

• Influence our product roadmap through direct customer insights.

• Bridge the gap between customer requirements and internal engineering execution.

• Work on cutting-edge AI infrastructure used by leading AI companies and developers.

• Solve challenging problems across inference, GPUs, agent systems, and distributed computing.

• Have direct impact on customers and product direction.

• Move fast in a highly technical and entrepreneurial environment.

• Collaborate with a team deeply passionate about the future of open AI infrastructure.

• Competitive pay package, 100% employer-covered premium medical, dental, and vision insurance, 401(k) plan, free meals in the office