AI Software Engineer

Stealth AI Research Lab; Cambridge (MA); On-site; USD 120,000 - 180,000; Full time

Job summary

Stealth AI Research Lab is seeking an AI software engineer to scale Cortex SDK/API and related products. You will collaborate with researchers and engineers, owning meaningful features from early weeks and contributing to production-grade software.

You’ll work on the Cortex SDK, API, and frontend, focusing on agent loops, tool calls, retrieval-based reasoning, and scalable cloud services. The role combines research and software engineering in a fast-moving startup environment.

Qualifications

• Degree in computer science or related field, or equivalent practical experience.
• 1–4 years of professional experience is ideal; exceptional newer grads are welcome.
• Strong software engineering fundamentals: clear, tested code, Git, code review, and issue tracking.
• Mastery of Python and/or TypeScript, experience building backend services and APIs.
• Familiarity with building LLM applications: retrieval-based systems, embeddings, and tool-using agents.

Responsibilities

• Build the core Cortex SDK, API, and products; work with researchers to implement algorithms.
• Improve the agent loop, planning, tool calls, and token-efficient performance.
• Backend development: design and ship services, data models and APIs on cloud infra (GCP).
• Polish the Cortex Studio frontend and other products for speed, reliability and delight.
• Raise the engineering bar: CI/CD, staging, test gates, safe rollouts, and monitored rollouts.

Skills

Python

TypeScript

Backend development

LLM applications

Retrieval systems

Git

Code review

Education

Bachelor's degree in Computer Science

Tools

Git

Jira

GCP

CI/CD

Job description

We are a team of neuroscientists, mathematicians, AI researchers and engineers on a mission to learn from the human brain and to build an AI that can learn continuously, in a sample efficient way, and reason about its knowledge. We are a seed-stage team with early commercial traction building Cortex . Cortex is in use by customers today, and we're scaling it into a platform that many products and teams can build on.

About us

We are a team of neuroscientists, mathematicians, AI researchers and engineers on a mission to learn from the human brain and to build an AI that can learn continuously, in a sample efficient way, and reason about its knowledge. We are a seed-stage team with early commercial traction building Cortex . Cortex is in use by customers today, and we're scaling it into a platform that many products and teams can build on.

The role

We're looking for an AI software engineer to help build and scale the Cortex SDK and API and the products we build on top (frontend and backend). You'll work closely with the founder and the rest of the engineering and research team, and you'll have real ownership from your first weeks.

What you'll do

• Build the core platform. Develop features in the Cortex SDK, API, and Products: Work with researchers to define and implement core algorithms related to knowledge formation, representation, and retrieval. Bring ideas to life, concretely.
• Work on the agent harness. Improve on our agent loop, planning, tool calls, and token-efficient performance.
• Backend development. Design and ship services, data models, and APIs on top of cloud infra (we use GCP), with attention to performance and correctness.
• Polish the product. Contribute to Cortex Studio frontend and other products to make them feel fast, reliable, and delightful.
• Raise the engineering bar. Help establish CI/CD, staging, test gates, safe rollouts, and rollback paths so we can ship quickly without breaking customers. You'll ship code that's used by customers.

What we're looking for

• A degree in computer science or a related field, or equivalent practical experience. 1–4 years of professional experience is ideal; exceptional newer grads are welcome.
• Strong software engineering fundamentals: you write clear, tested code and are comfortable with Git, code review, an issue tracking system (like linear or jira), and generally working together with other engineers in a professional environment.
• Good judgment and a sense of taste. We use coding assistants but hold a high bar. We are a no slop shop.
• Mastery of Python and/or TypeScript, experience building backend services and APIs.
• Familiarity with building LLM applications: you understand retrieval-based systems, embeddings, how to wire up a basic tool-using (ReAct-style) agent.
• Bias toward shipping. You're comfortable in a fast-moving environment where priorities shift.
• Clear communication, eagerness, humility, and a collaborative attitude.

Nice to have

• Publicly facing projects, demos, and/or open-source contributions involving LLMs and agents. Any sort of public record of having good ideas and implementing them.
• Interest in neuroscience, cognitive science, or machine learning research, or research experience in this space.
• Experience owning full software projects that hold up in high-stakes production environments: auth and RBAC, security and privacy, latency-sensitive paths, and the reliability habits (monitoring, safe rollouts, on-call) that come with real customers.

Why join

• Real ownership, early. You'll own meaningful pieces of the SDK, API, and Products built on them, and your work reaches the real world quickly.
• Close to the research. You'll work directly with neuroscientists, mathematicians, and AI researchers, and help turn their ideas into working software. You will learn a ton and have opportunities to develop more depth as an AI engineer.
• A hard, worthwhile problem. You'll be part of the team that builds the next generation of thinking machines.
• In person in Cambridge, MA. A small close-knit team in one room, with fast feedback and shared context. You’ll interact daily with our CEO (Harvard Neuroscience), as well as our AI researchers and engineers (ex Nasa and Google).

Equal opportunity employer.