AI Native Staff Engineer

# AI Native Staff Engineer at Carv

## About the role
We're looking for an experienced Staff Engineer who has built AI-native systems and shipped LLM-powered features to production. You're not a CRUD-endpoint writer anymore, but someone who architects and implements agentic AI systems.

## What you'll do

Build AI-Native Product Systems

• Design and ship AI-powered product features end-to-end
• Architect systems where LLMs, agents and traditional software work together
• Implement RAG pipelines, structured reasoning flows and tool-using agents
• Continuously improve reliability, latency and cost efficiency

Engineer With AI at Full Leverage

• Use AI agents to accelerate development, testing and architecture decisions
• Prototype rapidly and ship production-grade systems
• Set up internal AI tooling that multiplies team output
• Push the boundaries of what's possible with current models

Own Impact, Not Experiments

• Translate product problems into scalable AI-powered solutions
• Measure real-world performance (accuracy, business impact, UX)
• Optimize for production robustness, not just demo quality

Shape Our AI-Native Engineering Culture

• Raise the standard of how we use AI internally
• Establish pragmatic standards for evaluation and iteration
• Mentor engineers on AI-native workflows
• Contribute to long-term technical direction

## What we're looking for

Essential

• 8+ years of professional software engineering experience
• Proven track record designing and shipping large-scale production systems
• Experience owning architecture across services or product domains
• Strong backend engineering fundamentals (APIs, distributed systems, data modeling, concurrency, reliability)
• Experience operating systems in production (monitoring, incident handling, performance tuning)
• Cloud-native experience (GCP, AWS or Azure)
• Experience shipping LLM-powered features to real users in production
• Designed and implemented RAG systems in production environments
• Built or architected AI agents or tool-using multi-step reasoning systems
• Designed evaluation frameworks for LLM output quality, safety and regression detection
• Experience optimizing AI systems for latency, cost efficiency and reliability
• Experience integrating vector databases and embedding pipelines in scalable systems
• Active use of AI tools and agents to augment engineering workflows
• Demonstrated ability to design systems where AI components and deterministic systems work together
• Experience turning rapid AI prototypes into production-grade systems
• Strong judgment about when to use AI vs deterministic logic
• Experience leading complex technical initiatives end-to-end
• Ability to translate ambiguous business problems into system architecture
• Experience mentoring senior engineers or setting technical standards
• Track record of shipping high-impact features with measurable outcomes

What we consider less important

• Academic ML background
• Publishing papers
• Training models from scratch

## What we offer

• Very competitive compensation package
• Meaningful stock options
• Top-tier tools (MacBook Pro + AI tooling budget)
• Hybrid setup + occasional travel
• Make real impact
• Work directly with experienced SaaS leadership (15+ years in building)
• Real ownership over architecture and AI direction
• High-velocity, high-impact environment