Compensation: $180,000 - $220,000 | Equity Package

We’re looking for a Senior GenerativeAI Engineer who is also a strong senior backend engineer. This role works closely with Lead GenAI and Backend leadership and is responsible for building, extending, and operating GenerativeAI systems within our existing backend platform.

You will write new backend code, improve and refactor existing solutions, and contribute to production systems that serve real enterprise customers. You will work as part of a cross-functional engineering team and follow established software development best practices and processes.

Our AI-native platform is fundamentally transforming how enterprise revenue teams manage RFPs, security questionnaires, and compliance documentation—the critical bottleneck that delays deal closure and strains high-performing sales teams. We've engineered a solution that compresses weeks of manual work into minutes, delivering unprecedented speed and accuracy. Leading organizations including Corelight and BuildOps have already integrated our platform into their revenue operations.

We are executing against a massive market opportunity: over $10 trillion in annual transaction value flows through RFP processes, representing virtually unlimited automation potential.

ResponsibilitiesGenerativeAI Systems & Agents

• Design and build GenerativeAI-based agents integrated into existing backend services
• Extend and improve current GenerativeAI workflows, not just greenfield systems
• Build sophisticated agentic systems that unlock new product capabilities
• Enable agents to reason, call tools, and act within defined system boundaries

LLMOps & GenerativeAI Infrastructure

• Build, integrate, and maintain LLMOps tooling
• Make informed decisions on building vs buying GenerativeAI infrastructure components
• Support GenerativeAI experimentation frameworks for evaluating models, prompts, and workflows
• Ensure GenerativeAI systems are observable, debuggable, and production-ready
  

Prompt & Workflow Management

• Design and maintain efficient prompt management across models and use cases
• Version, test, and iterate on prompts and workflows safely in production
• Balance quality, consistency, latency, and cost
  

Models, Tools & GenerativeAI Workflows

• Work hands-on with inference models and embedding models
• Improve orchestration of multi-step GenerativeAI workflows
  

Measurement, Monitoring & Quality

• Define and track quality metrics for GenerativeAI workflows and agents
• Measure accuracy, consistency, and reliability across models and releases
• Design evaluation frameworks to compare new models, prompts, and workflows
• Ensure GenerativeAI changes are validated before rollout to production
  

Security, Safety & Guardrails

• Design and implement guardrails to prevent: Data leakage, Prompt injection, Data poisoning
• Ensure GenerativeAI systems adhere to security and privacy best practices
• Collaborate with backend and security teams to harden AI workflows

RequirementsGenerativeAI & LLMs

• Proven experience building production GenerativeAI systems
• Experience designing and operating agentic workflows
• Hands-on experience with inference and embedding models
• Experience building RAG-based systems and working with vector stores
  

LLMOps, Quality & Safety

• Experience implementing evaluation, monitoring, and experimentation for GenerativeAI systems
• Ability to reliably measure quality, consistency, and performance of GenerativeAI outputs
• Experience validating and comparing new models, prompts, and workflows
• Experience implementing safety and security guardrails for GenerativeAI systems

Backend Engineering

• Strong experience as a senior backend engineer in production environments, using Python
• Proven ability to write, review, and refactor backend code in collaborative codebases
• Experience integrating APIs, async workflows, and long-running processes
• Familiarity with the full software development lifecycle (SDLC)
• Design and implementation
• Code reviews and testing
• CI/CD, deployment, and monitoring

Infrastructure & Cloud

• Familiarity with AWS services, including Bedrock, EC2, ECS, S3, RDS
• Experience deploying and operating backend and GenerativeAI services in cloud environments

CI/CD & Engineering Practices

• Familiarity with CI/CD practices for both backend and GenerativeAI workflows
• Experience integrating testing, evaluation, and deployment into automated pipelines
• Strong adherence to engineering best practices, conventions, and maintainability

AI-Augmented Engineering

You are expected to actively use AI tools to increase development velocity.

You should be comfortable:

• Using AI coding assistants such as Cursor, Claude Code, and Copilot
• Applying LLMs for code generation, refactoring, debugging, and documentation
• Using AI tools to accelerate experimentation and iteration
• Maintaining high code quality while increasing throughput
  

Preferred Qualifications

• Experience working in fast-growing startups
• Familiarity with Model Context Protocol (MCP) or similar structured context and tool-integration approaches
• Experience designing internal GenerativeAI platforms or shared AI tooling

Benefits

• Health benefits package (including medical, dental, vision)
• Unlimited PTO
• Employee Assistance Program
• Flexible Spending Accounts
• 401(k)

Visa Sponsorship is not included in our hiring package. Applicants will need to be authorized to work in the U.S.