Principal Software Engineer, Breeze
J
JobgetherSoftware Engineering
United StatesFull-TimePrincipal
Salary$266,200–$425,900 USD
Apply NowOpens the employer's application page
Job Details
- Languages
- English
- Required Skills
- Generative AIDistributed Systems
Requirements
- Proven experience designing and scaling high-throughput, low-latency distributed systems with demanding reliability and concurrency requirements.
- Deep hands-on experience with generative AI technologies, including LLM orchestration, vector databases, RAG pipelines, and multi-agent frameworks.
- Strong understanding of model architecture trade-offs, fine-tuning approaches, inference costs, and practical considerations for deploying AI at scale.
- Demonstrated experience designing autonomous or semi-autonomous systems involving tool calling, complex state management, action execution, and graceful failure recovery.
- Strong platform-engineering mindset, with experience building reusable primitives, APIs, tools, or frameworks for other engineering teams and partners.
- Track record of delivering customer-focused products and balancing technical decisions with user experience and business outcomes.
- Ability to turn ambiguous problems into clear plans, working prototypes, and production-ready software without excessive process overhead.
- Curiosity and adaptability in a rapidly evolving AI landscape, with the ability to evaluate new models, research, and frameworks critically.
- Strong communication and technical leadership skills, with the ability to influence cross-functional stakeholders and mentor experienced engineers.
- Proficient written and spoken English.
- Professional experience with an object-oriented programming language.
- Ability to travel as required, including participation in regional in-person onboarding and team events.
Responsibilities
- Define scalable architecture and technical patterns for AI agents interacting safely with CRM data, agentic tools, memory, scheduled prompts, and third-party ecosystems.
- Establish the right balance between deterministic and non-deterministic workflows, optimizing for reliability, cost, trust, and outcome quality.
- Extend the AI platform to support new artifact types, internal builders, and high-value customer workflows across the broader product ecosystem.
- Partner with context and data-focused teams to ensure AI experiences are powered by complete, accurate, and actionable customer information.
- Rapidly prototype and validate emerging generative AI capabilities, including LLMs, RAG, and agentic frameworks, while determining when solutions are ready for production.
- Write and ship production-quality code while leading high-impact initiatives from early prototypes through reliable systems operating at scale.
- Establish strategies for AI evaluation, observability, privacy, guardrails, and reliability so customers can confidently use AI for meaningful business processes.
- Collaborate with Product, AI Research, Engineering, and Ecosystem teams to make internal tools and APIs accessible through the AI platform.
- Develop reusable platform primitives such as skills, tools, APIs, and agentic infrastructure that other teams can build upon.
- Mentor senior engineers and raise organizational fluency in prompt engineering, model selection, agentic architectures, and production AI systems.
View Full Description & ApplyYou'll be redirected to the employer's site
