Join a team focused on redefining how systems and domain engineers work with intelligent tools. As a Software Engineer specializing in AI/ML, you'll develop features that assist with drafting requirements, detecting inconsistencies, analyzing impacts, and offering actionable suggestions—directly integrated into engineering workflows.
What You’ll Do
- Design and deploy AI-driven capabilities that support requirement generation, validation, and change simulation for technical teams.
- Develop autonomous workflows enabling engineers to explore design options, test modifications, and verify specifications using intelligent agents.
- Assess and implement language models and supporting technologies, balancing performance, cost, and maintainability in live environments.
- Construct and manage core systems including data pipelines, model evaluation frameworks, prompt and version control, monitoring, and safety controls.
- Work across the entire stack—building backend services, APIs, and lightweight UI integrations—to deliver end-to-end AI functionality.
- Collaborate with product teams and users to uncover high-impact use cases, run rapid experiments, and refine features based on real-world usage.
What We’re Looking For
- At least three years of experience delivering machine learning or large language model features in production environments.
- Solid foundation in software engineering, with proven ability to design, test, and operate scalable services in the cloud.
- Hands-on familiarity with leading LLM platforms (e.g., OpenAI, Anthropic, Hugging Face), vector databases, and retrieval-augmented generation techniques.
- Experience crafting prompts, building retrieval-enhanced systems, evaluating model outputs, and implementing safeguards.
- Ability to weigh tradeoffs across models, architectures, and deployment strategies to make practical engineering decisions.
- Thrives in environments where ownership, rapid iteration, and learning from experiments are central.
Technology Environment
Our stack includes TypeScript and Node.js for frontend and backend services, Python for AI development, modern LLM APIs and orchestration tools, Postgres for data storage, and managed cloud infrastructure.
Our Approach
- Speed first: Build fast prototypes, then refine what proves valuable.
- End-to-end ownership: One person leads each feature from idea through production, with authority to simplify and prioritize.
- Foundations from day one: Evaluation, monitoring, and safety are built into every initial release.
Benefits
- Competitive salary and meaningful equity
- Health, dental, and vision insurance
- Flexible time-off policy
- Support for ongoing learning and engagement with the evolving AI landscape
