Forward Deployed Engineer Intern

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

We provide high-performance Model APIs, dedicated inference infrastructure, and Agent Sandbox environments that help developers and enterprises build, deploy, and scale production AI applications.

As a Forward Deployed Engineer Intern, you’ll work directly with customers to help them build and launch production AI systems.

You’ll sit at the intersection of engineering, customer success, and product, working alongside experienced engineers and GTM team members.

Unlike a traditional software engineering internship, much of your work will start with an actual customer problem.

A customer might need help understanding why an API is slow, scaling an inference workload, integrating a model endpoint, reproducing an error, or launching thousands of concurrent agent sandboxes.

Your job is to understand the problem, investigate it, and help drive it to resolution.

• Work directly with customers building AI products and agents.

• Help integrate Novita Model APIs, dedicated inference endpoints, and Agent Sandbox.

• Reproduce and debug customer issues involving APIs, networking, containers, Linux, and inference workloads.

• Investigate errors, latency, throughput, concurrency, and reliability issues.

• Build demos, integrations, scripts, PoCs, and reference implementations.

• Help customers move from experimentation into production.

• Partner with product, engineering, and SRE teams to resolve customer issues.

• Write documentation, runbooks, and internal tooling that make future deployments easier.

• Identify patterns across customer workloads and translate them into product improvements.

• Learn how customer usage, technical success, and business growth connect.

As you gain experience, you may independently own technical relationships with selected customers.

• Currently pursuing a Bachelor’s or Master’s degree in Computer Science, Computer Engineering, or a related technical field.

• Strong programming fundamentals.

• Proficiency in Python or another general-purpose programming language.

• Familiarity with Linux and APIs.

• Strong debugging and problem-solving ability.

• Comfortable communicating directly with customers.

• Ability to explain technical concepts clearly.

• High ownership and willingness to work through ambiguous problems.

• Available approximately 20 hours/week during the academic term or full-time during summer.

• Experience building applications using LLM APIs.

• Familiarity with Docker, Kubernetes, or cloud infrastructure.

• Experience with agent frameworks or coding agents.

• Familiarity with vLLM, SGLang, Ray, or other inference systems.

• Understanding of inference concepts such as latency, throughput, caching, batching, and concurrency.

• Hackathon projects, open-source contributions, or startup experience.

• Experience teaching, consulting, developer relations, or supporting technical users.

• Professional working proficiency in Mandarin Chinese.

During your internship, you will:

• Help real customers successfully deploy AI workloads.

• Become comfortable debugging production-facing problems.

• Build reusable tooling or documentation used by future customers.

• Develop strong intuition around how modern AI infrastructure works.

• Learn how engineering decisions affect customer adoption and business outcomes.