Forward Deployed Engineer New Grad

About Novita AI

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.

The Role

As a Forward Deployed Engineer, you’ll work directly with customers building some of the most demanding AI applications.

You’ll operate at the intersection of software engineering, infrastructure, product, and customer success.

You may spend one day helping an AI startup diagnose inference latency, another helping a coding-agent company scale thousands of sandbox environments, and another building an integration that becomes a reusable product capability.

You will be expected not only to solve technical problems, but also to understand why those problems matter to the customer and what is required for their workload to successfully reach production.

What You’ll Do

• Own the technical relationship with customers from evaluation through production.

• Understand customer architectures, workloads, and engineering requirements.

• Deploy and integrate:

  • Model APIs and inference endpoints
  • Dedicated model serving
  • Agent Sandbox environments

• Debug issues across APIs, containers, Linux, networking, model serving, and distributed systems.

• Analyze inference performance including latency, throughput, concurrency, caching, and reliability.

• Build customer-specific integrations, prototypes, tools, and automation.

• Support PoCs and help customers transition into production.

• Work closely with Technical Account Executives on capacity planning, quotas, pricing considerations, and workload expansion.

• Identify opportunities where customers can expand their usage of Novita.

• Translate recurring customer problems into product requirements.

• Build reusable tooling and reference implementations that improve the experience for future customers.

• Work closely with engineering teams across the US and Asia.

What We’re Looking For

Requirements

• Bachelor’s or Master’s degree in Computer Science, Computer Engineering, or a related technical field.
• Strong software engineering fundamentals.
• Proficiency in Python and experience with at least one additional programming language.
• Strong understanding of APIs, Linux, networking, and cloud-native applications.
• Experience debugging complex technical systems.
• Strong written and verbal communication skills.
• Comfortable working directly with customers.
• High ownership and ability to operate in ambiguous environments.
• Ability to move quickly between engineering, product, and customer problems.

Nice to Have

• Experience with LLMs, AI agents, or inference infrastructure.
• Familiarity with vLLM, SGLang, Ray, or distributed serving frameworks.
• Experience with Docker and Kubernetes.
• Understanding of model serving performance, including batching, caching, throughput, latency, and concurrency.
• Experience building coding agents, AI agents, or sandboxed execution systems.
• Open-source contributions, startup experience, or significant technical side projects.
• Background in solutions engineering, developer relations, technical consulting, or other customer-facing technical roles.
• Interest in the commercial side of technology, including how usage, pricing, and product adoption connect.
• Professional working proficiency in Mandarin Chinese.

What Success Looks Like

Within your first year, you will:

• Independently own the technical relationship with multiple customers.
• Help strategic customers successfully move workloads into production.
• Become a trusted technical advisor to customer engineering teams.
• Build reusable solutions that accelerate future deployments.
• Identify technical and product opportunities that increase customer adoption.
• Influence Novita’s product roadmap through direct exposure to real production workloads.