Sr Ai Engineer

*Senior AI Engineer *
Location: San Francisco(Hybrid) Experience: 8+ years Team: AI
Engineering

About Revi
Revi is a Series A restaurant commerce platform building the AI operating system for the restaurant industry. We're rapidly transforming how restaurants run their business through agentic AI — from voice agents that handle customer interactions to agentic commerce and intelligent automations across our ReviOS dashboard. We're a small, fast-moving team where engineers ship to production daily and own meaningful surface area from day one.
The Role
We're hiring a Senior AI Engineer to architect, build, and own production-grade agentic AI systems at Revi. You'll lead the design of single-agent and multi-agent systems that take real actions for restaurants and their customers, own the deterministic ML stack that powers personalization and decisioning across the product, and set the bar for how we deploy, monitor, and evolve AI in production. This is an IC role for a builder who has shipped — repeatedly — and knows what production reliability for AI systems actually requires.
What You'll Do
Architect and ship agentic AI systems end-to-end — designing single-agent and multi-agent topologies, tool interfaces, memory and state management, evaluation harnesses, and the production infrastructure that holds it all together
Own the deterministic ML modeling stack — feature pipelines, training, ranking/retrieval, evaluation, and online serving for high-traffic use cases
Drive integration with LLM providers (Claude, GPT, and others) at production scale — handling latency, cost, reliability, prompt iteration, structured outputs, function/tool calling, and provider failover
Own production deployment and operations: CI/CD, containerization, observability, on-call quality, cost monitoring, and graceful degradation strategies for AI systems
Set technical direction and review architectural decisions across the AI Engineering team; mentor junior engineers and raise the engineering bar
Partner with product and leadership to translate Revi's growth strategy into concrete AI roadmaps
What We're Looking For
Basic Qualifications
6+ years of professional work experience building and shipping ML/AI systems in production. Personal projects, hackathons, and class work do not substitute for this requirement — we need engineers who have operated AI in real production environments at meaningful scale
Deep, hands-on experience with agentic AI — you have personally architected and shipped single-agent or multi-agent systems in a production setting. You can speak fluently about tool use, planning loops, evaluation, failure modes, and the tradeoffs between orchestration patterns
Strong deterministic ML modeling background — production experience training and serving classification, ranking, retrieval, or recommendation models. Familiarity with the full ML lifecycle: data, features, training, evaluation, serving, monitoring
Production experience with LLM providers (Anthropic Claude, OpenAI GPT, or equivalent) — not just API calls, but production integration including prompt engineering at scale, tool use, structured outputs, evaluation, cost control, and reliability engineering
Production deployment experience is critical and non-negotiable — you have personally owned services running in production, including CI/CD, containerization (Docker/Kubernetes), cloud infrastructure (AWS/GCP/Azure), monitoring/observability, and on-call. Candidates without demonstrable production deployment ownership will not be considered
Hands-on production experience with large-scale data processing tools — including distributed batch processing (Spark, Databricks, or equivalent) and streaming/event pipelines (Kafka, Kinesis, Pub/Sub, Flink, or equivalent). You have built and operated real data pipelines feeding ML/AI systems at scale, not just consumed pre-processed datasets
Excellent Python, strong fundamentals in distributed systems, data engineering, and modern cloud infrastructure
BS, MS, or PhD in Computer Science, Machine Learning, or a related quantitative field — or equivalent professional track record
Preferred Qualifications
Prior Staff or Tech Lead experience at a high-growth startup or a top-tier tech company
Experience with voice AI, real-time conversational systems, or speech-to-text/text-to-speech pipelines
Deep experience with vector databases, retrieval systems, and large-scale RAG architectures
LLM observability and evaluation tooling expertise (LangSmith, Langfuse, custom eval frameworks)
Experience in restaurant tech, commerce platforms, or B2B SaaS at scale
Experience fine-tuning, distilling, or post-training open-weight models for production
Why Revi
Architect and own the AI systems powering a category-defining restaurant commerce platform
Direct partnership with leadership on technical strategy and product direction
Ship to real customers at startup speed — meaningful equity and meaningful surface area
Strong, AI-forward engineering culture with high autonomy and high standards
Our Values
Heart: A team that is passionate about what they do, with a heart of giving back.
Impact: Being a versatile team player with an innovative mind and a firm backbone to make an impact on everything they touch.
Excellence: A team committed to excellence in all we do, with integrity and supreme service.
Perks and Benefits of Joining the Revi Team
Architect and own the AI systems powering a category-defining restaurant commerce platform
Direct partnership with leadership on technical strategy and product direction
Ship to real customers at startup speed — meaningful equity and meaningful surface area
Strong, AI-forward engineering culture with high autonomy and high standards
Competitive compensation, meaningful early-stage equity, and a strong AI-forward culture
Excellent and comprehensive health plans (Medical, dental, vision, etc)
Flexible Vacation Policy, Paid holidays
Organized volunteer events to give back to our community
Off-sites,