AI Full-Stack Engineer Jobs

View detail

The Senior Software Engineer will build a powerful project innovating customer support by defining what an AI-first SaaS product looks like, addressing unique UI/UX, capabilities, and data model challenges of an AI-first company. They will lead ambitious and ambiguous projects involving strong technical decision-making, effective implementation, and incorporate product and design instincts. The engineer will work across the tech stack, collaborate with a top-caliber team, and mentor or lead less experienced engineers. They will participate in an engineering-led culture where everyone owns working with users and building a great product, taking ownership of challenging problems and defining and implementing solutions.

View detail

Design a collaborative "Multiplayer Computer" that lets humans and AI agents work together on shared shells, filesystems, and state—conflict-free and in real time; build high-throughput backend applications and services; create tooling that helps AI systems minimize mistakes through static analysis and deterministic techniques; develop infrastructure (frontend & backend) that empowers product engineers to rapidly ship delightful user experiences; support sophisticated user interfaces, including terminals, code editors, window-management systems, and innovative experiences that require both creativity and algorithmic skill; and bridge the gap between prompt engineers and frontend engineers. Telecommuting is permitted with in-office presence required three times a week (Monday, Wednesday, Friday), with only incidental domestic travel required.

View detail

Design and build GenAI systems that turn large language models (LLMs) into composable, dependable tools, leveraging retrieval, tool use, agentic reasoning, and structured outputs. Collaborate with ML and infrastructure engineers to scale and optimize GenAI workflows, manage latency, context windows, and model choice. Write high-quality, modular code that handles failure gracefully, is flexible to change, and easy to iterate on. Own major architectural decisions regarding workflow architecture, data flow, caching, and structuring generative outputs. Drive rigorous evaluation by building benchmark datasets, developing automated and human-in-the-loop evaluation frameworks, designing experiments to identify failure modes and edge cases, conducting A/B tests to inform deployment, and using clinician feedback to guide model improvement. Prototype rapidly with new models, open-source tools, and novel prompting techniques. Own the end-to-end productionization of LLM workflows: deploy models in low-latency, high-uptime environments, build monitoring and observability systems, implement post-processing guardrails, and manage workflow versioning.

View detail

Build systems that integrate with the EHRs used in American healthcare to make Heidi feel like a native capability rather than a plugin. Develop systems that simplify the complexity of US healthcare billing, compliance, and payer constraints so clinicians do not have to manage these complexities. Write clean, testable code with strong interfaces, error handling, and observability, ensuring the workflows are reliable for clinicians, operators, and downstream systems. Focus on outcomes by ensuring that the built systems help clinicians and improve practice revenue. Create agentic workflow functionalities where AI assists with extraction, reconciliation, and drafting within workflows, incorporating human review, auditability, and control. Collaborate closely in a team environment with frequent pairing and shared ownership of design and implementation. Learn about healthcare organizational operations, especially those serving US customers, to translate requirements and constraints into product improvements.

View detail

Create functional black box tests for large codebases in various source languages. Create and manage Docker environments to ensure 100% reproducible builds and test execution across different platforms. Monitor code coverage and configure automated scoring criteria to meet industry benchmark-level standards. Leverage LLMs such as Roo Code and Claude to accelerate development cycles, automate repetitive tasks, and improve overall code quality.

View detail

Create functional black box tests for large codebases in various source languages; create and manage Docker environments to ensure 100% reproducible builds and test execution across different platforms; monitor code coverage and configure automated scoring criteria to meet industry benchmark-level standards; leverage LLMs (Roo Code, Claude) to accelerate development cycles, automate repetitive tasks, and improve overall code quality.

View detail

Create functional black box tests for large codebases in various source languages. Create and manage Docker environments to ensure 100% reproducible builds and test execution across different platforms. Monitor code coverage and configure automated scoring criteria to meet industry benchmark-level standards. Leverage LLMs (Roo Code, Claude) to accelerate development cycles, automate repetitive tasks, and improve overall code quality.

View detail

Create functional black box tests for large codebases in various source languages; create and manage Docker environments to ensure 100% reproducible builds and test execution across different platforms; monitor code coverage and configure automated scoring criteria to meet industry benchmark-level standards; leverage LLMs such as Roo Code and Claude to accelerate development cycles, automate repetitive tasks, and improve overall code quality.

View detail

Create functional black box tests for large codebases in various source languages. Create and manage Docker environments to ensure 100% reproducible builds and test execution across different platforms. Monitor code coverage and configure automated scoring criteria to meet industry benchmark-level standards. Leverage LLMs (Roo Code, Claude) to accelerate development cycles, automate repetitive tasks, and improve overall code quality.

View detail

Create functional black box tests for large codebases in various source languages. Create and manage Docker environments to ensure 100% reproducible builds and test execution across different platforms. Monitor code coverage and configure automated scoring criteria to meet industry benchmark-level standards. Leverage large language models (LLMs) like Roo Code and Claude to accelerate development cycles, automate repetitive tasks, and improve overall code quality.