This hybrid role is based in Santa Clara, CA, and requires 2 days per week in the Santa Clara office.
The role includes support for US regulated markets.
As a staff (IC4) engineer, you lead the design, build and delivery of complex AI-native and cloud-native systems on your own.
You take ownership of critical components or features, set technical direction in your domain, and serve as a go-to technical resource for peers and junior engineers.
The work pairs solid software engineering with hands-on AI/ML integration, cloud architecture and production operations, and requires you to weigh technical depth against wider impact across teams on unclear problems and platform improvements.
Responsibilities
Lead the design and architecture of production-critical AI-native systems, such as LLM integrations, agent workflows, retrieval pipelines and inference services.
Take medium to large features or systems from specification through design, build, testing, deployment and production monitoring.
Weigh latency, cost, scalability, reliability and model quality when making architecture and trade-off decisions.
Set up evaluation frameworks, test strategies and production monitoring for AI features, and push teams toward eval-driven development.
Design and tune high-performance data pipelines, embedding systems and vector stores that handle millions of rows and complex retrieval.
Champion security practices covering prompt-injection defense, data privacy, PII handling, responsible AI guardrails and regulatory compliance.
Join cross-team architecture reviews and help shape platform-level technical decisions.
Track emerging AI/ML frameworks, services and techniques, and recommend which ones to adopt.
Mentor junior and mid-level engineers (IC2/IC3) through pairing, design reviews, architecture discussions and hands-on coaching.
Review code thoroughly, including prompts, agent logic, retrieval strategies and AI model behavior.
Spot technical debt and improvement areas, and drive efforts to address them.
Share knowledge through documentation, brown-bag sessions and architecture guidance, and help with onboarding and interview assessments of candidates.
Build well-tested software in Python, Java and JavaScript as needed, including unit tests, integration tests and AI evaluation harnesses for accuracy, regression and hallucination detection.
Diagnose issues across distributed systems, probabilistic models and cloud infrastructure, and isolate root causes quickly.
Manage deployments and production monitoring, respond to performance problems and model drift, and iterate on features.
Work with AWS, GCP or Azure, managed AI services such as Bedrock, Vertex AI and Azure OpenAI, Kubernetes and CI/CD pipelines.
Build custom applications, extensions and integrations on the company platform, including workflows, business rules and automation written in the company scripting.
Create data models, forms and dashboards for the company applications, tune database queries, and integrate third-party AI/ML services and custom APIs.
Maintain the company plugin and app architecture, take part in upgrades and configuration management, and mentor engineers on platform patterns.
Join triage and root cause analysis for production the company issues, and work with customer success and support teams on complex problems.
Guide customers on application usage, configuration and troubleshooting, spot recurring issues, contribute to documentation, and handle critical escalations.
Work with product, domain specialists and engineering teams to define requirements and technical specifications, and explain AI trade-offs to non-technical stakeholders.
Lead root cause analysis for customer-reported issues, including hallucinations, retrieval quality and model behavior, and pass customer feedback to product management.
Requirements
8+ years of software development experience with a Bachelor's degree, 6+ years with a Master's degree, 3+ years with a PhD, or equivalent work experience.
5+ years of practical experience with modern cloud-native and AI-native systems.
3+ years of hands-on work with LLM prompt engineering, agent design and retrieval systems such as RAG, semantic search and knowledge bases.
3+ years of proven experience integrating third-party AI/ML services and platform APIs, such as OpenAI, Anthropic, AWS Bedrock or Google Vertex AI.
2+ years of hands-on experience building applications and extensions on the company platform.
Strong skills in JavaScript/GlideScript, Python and Java, with familiarity in the company scripting patterns and APIs.
Solid knowledge of the company data model, form and workflow design, and business process automation.
Solid knowledge of microservices, REST and streaming APIs, and backend frameworks such as Spring Boot and FastAPI.
Experience designing and tuning high-performance data pipelines, embedding systems and vector stores at scale.
Proven expertise with LLM orchestration frameworks (LangChain, LlamaIndex, Semantic Kernel) and vector databases (Pinecone, Weaviate, pgvector, etc.).
Experience with cloud platforms and managed AI services (AWS, GCP, Azure), plus hands-on infrastructure-as-code.
Proficiency with Kubernetes, containerization, CI/CD pipelines and automated testing frameworks.
Experience building and debugging evaluation harnesses, benchmarks and metrics for AI/ML features.
Proven ability to find and isolate root causes in complex, distributed and probabilistic systems.
Strong communicator who can explain technical concepts to technical and non-technical audiences; customer-facing experience a plus.
Familiarity with Agile and Scrum, and comfort iterating and improving continuously.
Demonstrated ability to engage customers, understand their needs and support issue resolution.
Track record of owning significant technical initiatives and delivering them successfully.
Demonstrated mentorship of junior engineers or technical leadership in previous roles.
Conditions
Hybrid work in Santa Clara, CA, with 2 days per week in the Santa Clara office.
Base pay is $176,100 - $308,200, as a guideline; individual total compensation varies by qualifications, skill level, competencies and work location.
Pay also includes equity when applicable, variable or incentive compensation, and benefits.
Compensation depends on the geographic location of the role and may change based on work location.
Work personas (flexible, remote or required in office) are assigned based on the nature of the work and work location, and eligibility may be checked by measuring the distance from your primary residence to the nearest office with a third-party service.
Benefits
Health plans, including flexible spending accounts.