Lead AI Engineer
Job description
Lead AI Engineer at Sierra Studio.
About the role
You will architect the software stack and oversee the technical implementation of AI initiatives, translating ambiguous product ideas into robust production systems. You will prompt engineer large language models to solve real-world problems while establishing the evaluation frameworks that measure their effectiveness and reliability. You will partner closely with product managers and designers to iterate on concepts rapidly and guide them from initial sketches to deployed features. You will mentor other engineers, elevating the technical capabilities of the team and fostering a culture of experimentation and ownership. You will help interview and grow future talent, shaping the technical bar for new hires as the team expands. You will contribute to multiple projects concurrently, balancing client work with internal innovation to keep the pipeline of ideas flowing. You will take ownership of the entire product lifecycle for AI features, ensuring solutions are scalable, maintainable, and aligned with client and user needs. As an early employee, your work will directly define the engineering culture and set the standards for how AI products are built at Sierra Studio.
Key facts
What you'll do
- Explore raw client concepts and translate them into technical specifications for AI-powered products.
- Design and maintain the backend architecture that supports LLM integrations, ensuring performance and security.
- Implement prompt engineering pipelines and retrieval-augmented generation workflows to enhance model accuracy.
- Build and refine evaluation suites that continuously measure the quality and safety of model outputs.
- Collaborate with product managers to prioritize features and align technical constraints with business goals.
- Lead code reviews and pair programming sessions to elevate the overall quality of the codebase.
- Coordinate with designers to ensure AI features deliver intuitive and seamless user experiences.
- Own the deployment pipeline, monitoring tools, and debugging processes for production AI systems.
- Mentor junior engineers and facilitate knowledge sharing sessions to strengthen the team's expertise.
- Research and prototype new AI capabilities to keep Sierra Studio at the forefront of the field.
- Manage time across multiple projects, switching context efficiently without sacrificing quality.
- Document systems and processes so that solutions are understandable and maintainable by the whole team.
- Communicate clearly with stakeholders in English, providing updates and gathering feedback on a regular basis.
- Identify bottlenecks in model performance and work with the team to iterate on solutions.
Requirements
- You have shipped real-world applications powered by large language models in professional or personal projects.
- You possess experience with prompt engineering, retrieval-augmented generation, and agentic AI patterns.
- You have built evaluation methods for LLM-powered products, including metrics and testing strategies.
- You demonstrate a growth mindset, learning new AI tools, frameworks, and research quickly.
- You have led technical direction for products, whether through formal titles or informal ownership.
- You can work effectively with product, design, and other stakeholders to align on goals and tradeoffs.
- You are comfortable managing multiple projects at the same time without losing focus on quality.
- You communicate fluently in English, both in writing and in verbal discussions with US-based clients.
- You are proficient in backend development, with hands-on experience in Python (e.g., FastAPI) or TypeScript.
- You understand software best practices such as testing, version control, and modular architecture.
- You are able to translate high-level product ideas into concrete technical tasks and implementation plans.
- You care about user needs and build technology that solves tangible problems rather than chasing trends.
- You are comfortable working in a fully remote environment with flexible hours focused on output.
Nice to have
- Experience with fine-tuning large language models for specific domains or tasks.
- Curiosity about the latest advances in AI research and how they can be applied to real products.
- Experience using AI-assisted development tools such as Cursor or Claude Code to boost your coding workflow.
Practical notes
This is a full-time, fully remote role based in Brazil with flexible hours focused on results rather than online presence. The position requires comfort with asynchronous communication and a proactive approach to managing workload. Travel is not required, and there are no visa sponsorship needs for candidates located in Brazil. The start date is flexible, and the schedule will be determined in coordination with the hiring team.