The role is for a Staff Software Engineer (IC4) who leads the design, build and delivery of complex, high-impact AI-native and cloud-native systems. You take ownership of critical components or features, set technical direction in your area, and act as a technical go-to for peers and junior engineers.
The work calls for strong software engineering fundamentals alongside hands-on skill in AI/ML integration, cloud architecture and production systems. You will balance deep technical work with broader organizational impact, cooperate across teams on ambiguous problems, and drive platform improvements.
Responsibilities
Lead design and architecture of complex, production-critical AI-native systems, such as LLM integrations, agentic workflows, retrieval pipelines and inference services.
Own medium-to-large features or systems end to end: specification, design, implementation, testing, deployment and production monitoring.
Make architectural and technical trade-offs among latency, cost, scalability, reliability and model quality.
Build evaluation frameworks, testing strategies and production monitoring for AI-driven features, and drive adoption of eval-driven development.
Design and optimize high-performance data pipelines, embedding systems and vector stores that handle millions of rows and complex retrieval.
Champion security practices including prompt-injection defense, data privacy, PII handling, responsible AI guardrails and regulatory compliance.
Take part in cross-team architecture reviews and help shape platform-level technical decisions.
Track emerging AI/ML frameworks, services and techniques, and evaluate and recommend adoption where it fits.
Mentor junior and mid-level engineers (IC2/IC3) through pair programming, design reviews, architecture discussions and hands-on coaching.
Review code thoroughly, including prompts, agent logic, retrieval strategies and AI/model behavior validation.
Find technical debt and improvement opportunities, then lead initiatives to address them.
Share knowledge through documentation, brown-bag sessions and architectural guidance, and help onboard new team members.
Help with hiring by interviewing engineering candidates and giving technical assessments and feedback.
Model good craftsmanship, testing discipline and debugging method for the team.
Work with product management, domain specialists and other engineering teams to define requirements and technical specifications.
Explain complex technical concepts and AI trade-offs to non-technical stakeholders such as product, leadership and customers.
Lead root cause analysis for customer-reported issues, including model behavior, hallucinations, retrieval quality and distributed system faults.
Join design reviews, planning sessions and retrospectives, and give input on feasibility and risk.
Communicate clearly about design decisions, implementation problems, AI limitations and production incidents.
Build and maintain relationships with adjacent teams and external partners where relevant.
Look for ways to improve development processes, tooling and team efficiency.
Write robust, maintainable, well-tested AI-native software in Python, Java and JavaScript as appropriate.
Build unit tests, integration tests and AI evaluation harnesses covering accuracy, regression and hallucination detection.
Troubleshoot complex issues across distributed systems, probabilistic models and cloud infrastructure, and isolate root causes quickly.
Apply secure coding practices and responsible AI guardrails throughout the development lifecycle.
Manage deployment, monitoring and iteration of production features, responding to performance problems and model drift.
Work with AWS, GCP or Azure, managed AI services (Bedrock, Vertex AI, Azure OpenAI), Kubernetes and CI/CD pipelines.
Contribute to code and architecture standards and make sure they are followed.
Design and build custom the company applications, extensions and integrations.
Write the company workflows, business rules and automation using JavaScript, GlideScript and REST APIs.
Build data models, forms and dashboards for the company applications, and tune database queries for speed.
Connect third-party AI/ML services and custom APIs to the company platform services.
Build and maintain the company plugin and app architecture following platform best practices and coding standards.
Take part in the company upgrades and configuration management, keeping work compatible with platform updates.
Mentor junior engineers on the company capabilities and development patterns.
Join customer issue triage and root cause analysis for production the company applications.
Work with customer success and support teams to resolve complex technical problems.
Give customers technical guidance on application usage, configuration and troubleshooting.
Spot patterns in customer issues and drive changes that prevent them from recurring.
Contribute to customer documentation and internal knowledge bases.
Support customer escalations and resolve critical issues affecting customer operations quickly.
Collect customer feedback and pass product improvement opportunities 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 software development experience on modern cloud-native and AI-native systems.
3+ years of hands-on work with LLM prompt engineering, agent design and retrieval systems (RAG, semantic search, knowledge bases).
3+ years of proven experience integrating third-party AI/ML services and platform APIs such as OpenAI, Anthropic, AWS Bedrock and Google Vertex AI.
2+ years of hands-on experience building applications and extensions on the company platform.
Strong skill in JavaScript/GlideScript, Python and Java, with familiarity with the company scripting patterns and APIs.
Solid grasp of the company data model, form and workflow design, and business process automation.
Solid grasp of microservices architecture, 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.
Demonstrated depth in LLM orchestration frameworks (LangChain, LlamaIndex, Semantic Kernel) and vector databases (Pinecone, Weaviate, pgvector, etc.).
Experience with AWS, GCP or Azure and their managed AI services, plus hands-on infrastructure-as-code work.
Proficiency with Kubernetes, containers, CI/CD pipelines and automated testing frameworks.
Experience building and debugging evaluation harnesses, benchmarks and metrics for AI/ML features.
Proven ability to troubleshoot and isolate root causes in complex, distributed and probabilistic systems.
Strong communication skills for both technical and non-technical audiences. Customer-facing experience is a plus.
Experience with Agile and Scrum, and comfort with iterative development and continuous improvement.
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
Base pay for this location is $176,100 - $308,200, plus equity where applicable, variable or incentive compensation, and benefits. Pay is based on the geographic location of the role and may change with work location. The base pay shown is a guideline, and individual total compensation varies with qualifications, skill level, competencies and work location.
Work persona (flexible, remote or required in office) is assigned based on the nature of the work and the assigned work location. The company may check the distance between your primary residence and the nearest office using a third-party service to determine eligibility.
Sales positions generally offer a competitive On Target Earnings (OTE) incentive structure, though this role is not described as a sales position.
Benefits
Health plans, including flexible spending accounts.
401(k) plan with company match and an employee stock purchase plan (ESPP).
Matching donations.
Flexible time away plan and family leave programs.