Staff Software Engineer, AI Foundations
Leads development of systems that optimize AI agents for cost, latency, and quality, with emphasis on agentic coding and reliable production software. Requires 8+ years of experience, strong concurrency and API design skills, and fluency in multiple programming languages.
About the job
Responsibilities
- Lead agent optimization efforts for AI applications, improving token spend and response time while maintaining result quality.
- Design and build reliable agentic coding systems that deliver high-quality outputs.
- Apply AI application development patterns and emerging architectures, including model routing, multi-agent architectures, caching policies, and context management.
- Own new features end to end, collaborating across teams to deliver reliable features and strong developer experiences.
- Work with Python, TypeScript, Java, and Go.
- Serve as an AI design-pattern domain expert and collaborate with field staff on best practices and canonical examples.
- Debug complex issues for the developer community and gather feedback on product features and APIs.
- Write public technical documentation for concepts and APIs.
- Provide occasional expert customer support and attend periodic coworker meetings or developer conferences.
Requirements
- 8+ years of professional work experience.
- Proven experience optimizing AI systems using machine learning and systems techniques.
- Experience with and passion for generative AI, especially agents and coding applications.
- Fluency in multiple programming languages and willingness to learn new ones.
- Deep experience with concurrent programming, including safe use of mutexes, atomics, and other concurrency primitives.
- Experience designing APIs and documenting publicly available libraries or modules.
- Strong written and verbal technical communication skills in English.
- Bachelor's or master's degree in Computer Science or a closely related field, or equivalent professional experience.
Nice to Have
- Familiarity with Temporal's programming model.
- Open source contributions, including contributions to third-party libraries.
- Experience contributing to large-scale distributed-systems architecture and design.
- Background in machine learning, model training, data science, or machine-learning systems.
- Graduate degree in Computer Science.
Skills
Python, TypeScript, Java, Go, Generative AI, AI Agents, Machine Learning, Concurrent Programming, Mutexes, Atomics, API Design, Distributed Systems, Open Source
Similar jobs
ML Engineering jobs
OnePay
United States
Design and productionize ML, deep learning, and LLM models for personalization, recommendations, and search systems. Requires 7+ years building production ML/AI with business impact and strong cross-functional collaboration skills.
Talkiatry
United States
Staff-level engineer responsible for building AI agents and automation, evaluating developer AI tools, and driving adoption across the engineering organization. Requires 8+ years of software engineering experience plus production experience with LLMs, agentic systems, and applied machine learning.
Grafana Labs
United StatesBuilds and owns production multi-agent AI infrastructure, backend integrations, and workflow automation for marketing operations. Requires 8+ years of software engineering experience, strong Python and JavaScript/Node.js skills, production LLM experience, and deep Google Cloud expertise.
Nuro
Mountain View, CA
Develop and productize online mapping models for autonomous navigation using real-world sensor data. The role requires deep ML expertise, robotics or computer vision experience, strong Python and deep learning framework skills, and a staff-level ability to deliver practical solutions.
Nuro
Mountain View, CA
Build and operate ML infrastructure for autonomy teams, including training and deployment pipelines, model observability, inference serving, and compiler platforms across hardware targets. Requires a degree, 3+ years of relevant experience, Python proficiency, and distributed-systems expertise.