Software Engineer

Emissary; San Francisco (CA); On-site; USD 120,000 - 180,000; Full time

Job summary

Emissary is building frontier-quality AI platforms that optimize LLM requests across models, with dedicated compute and post-training capabilities. We’re looking for a Product Engineer who will own features end-to-end—from UI to APIs to infrastructure—at scale.

You’ll work with customers and the founding team to translate real usage into product decisions, shipping on committed timelines and shaping the architectural direction as the team grows.

Qualifications

• Solid software engineering fundamentals: data structures, algorithms, and system design.
• Experience building production web applications with a modern frontend framework (React/Next.js) and TypeScript.
• Back-end experience with Python, Go, or TypeScript/Node, including APIs, databases, and service integration.
• Familiarity with cloud platforms (AWS, GCP, or Azure) and containerization (Docker, Kubernetes).
• Experience with LLM APIs, inference systems, ML pipelines, or distributed systems is a plus.
• BS in Computer Science, Engineering, or related field, or equivalent practical experience.

Responsibilities

• Build customer-facing product surfaces, including the web app, playground, dashboards, and developer experience.
• Design and ship back-end services and APIs that power routing, serving, evaluation, and post-training workflows.
• Work on the infrastructure behind high-volume, low-latency inference: dedicated compute, tenant isolation, observability, and reliability.
• Own features from spec to production, and stay with them through monitoring, iteration, and customer feedback.
• Help shape architecture and engineering practices as the team grows.

Skills

React/Next.js

TypeScript

Python/Go/Node

Docker

Kubernetes

LLM APIs / ML pipelines

Education

BS in Computer Science, Engineering, or related field

Tools

AWS

Docker

Kubernetes

Job description

Emissary gives teams frontier-quality AI at open-source prices. Our platform optimizes every LLM request in three ways: it routes each step of a task to the best model for the job across open and closed models, serves open models on dedicated compute tuned to each customer's traffic, and post-trains custom models on the trajectories customers already generate. The more a customer routes, the more data they have to train on, and the cheaper and better their AI gets.

We're already running in production inside the agent stacks of fast-growing AI companies and enterprises, handling 30M+ requests and around 100+B tokens a month under a 99.99% uptime SLA.

The Role

We're a small team, and we're looking for a Product Engineer who wants to own features end to end, from the UI a customer clicks on, to the APIs behind it, to the infrastructure that keeps it fast and reliable at scale. You won't be boxed into one layer. One week you might be building playground and dashboard experiences, the next you might be shipping routing logic or tuning inference capacity.

You'll work directly with customers and the founding team, turning real usage into product decisions and shipping on committed timelines.

What you'll do

• Build customer-facing product surfaces, including the web app, playground, dashboards, and developer experience.
• Design and ship back-end services and APIs that power routing, serving, evaluation, and post-training workflows.
• Work on the infrastructure behind high-volume, low-latency inference: dedicated compute, tenant isolation, observability, and reliability.
• Own features from spec to production, and stay with them through monitoring, iteration, and customer feedback.
• Help shape architecture and engineering practices as the team grows.

Who you are

• Diligent and hardworking. You sweat the details, follow through on commitments, and take pride in shipping things that work.
• Genuinely excited about AI infrastructure, including model routing, inference serving, and post-training. You don't need to be an expert on day one, but you should be eager to go deep fast.
• Flexible across the stack and happy to pick up whatever the product needs most.
• Customer-minded. You care as much about solving the user's problem than writing the perfect abstraction.
• Comfortable giving and receiving frequent, direct feedback.
• Fun to be around - startups are intense, helps to enjoy the company of those around you!

Qualifications

• Solid software engineering fundamentals: data structures, algorithms, and system design.
• Experience building production web applications with a modern frontend framework (e.g., React, Next.js) and TypeScript.
• Back-end experience with at least one language such as Python, Go, or TypeScript/Node, including APIs, databases, and service integration.
• Familiarity with cloud platforms (AWS, GCP, or Azure) and containerization (Docker, Kubernetes).
• Experience with LLM APIs, inference systems, ML pipelines, or distributed systems is a plus.
• BS in Computer Science, Engineering, or a related field, or equivalent practical experience.