Skip to content
RetoolRetoolSan Francisco, CA

Software Engineer, AI Product Engineer

Builds AI-powered features for developer tools, including generative UIs from natural language, LLM performance improvements, and RAG patterns. Requires 3+ years experience with LLMs, modern AI techniques, and full-stack engineering in TypeScript/Node.js/React.

164k – 306k/yr
Hybrid3+ YOEML Engineering

About the role

What You'll Do

  • Build generative UIs that let users create real apps from natural language
  • Improve the performance, observability, and safety of our internal model architecture
  • Extend our AI evaluation systems to support smarter ranking, feedback loops, and product metrics
  • Develop patterns for retrieval-augmented generation (RAG), few-shot prompting, and agentic architecture
  • Contribute to building internal tools that help us accelerate iteration on AI features and workflows

You'll work in a TypeScript + Node.js + React stack.

The Skillset You'll Bring

  • 3+ years of professional software engineering experience
  • A track record of building and shipping real product—not just models or papers
  • Experience working with LLMs and modern techniques (RAG, CoT, few-shot, embeddings, etc.)
  • An eye for product: you care how features work and how they feel
  • Familiarity with vector databases, prompt orchestration tools, and evaluation techniques
  • A pragmatic mindset about what’s scalable and maintainable in production

Nice to Have

  • Experience in JavaScript / TypeScript
  • Experience with PostgreSQL
  • Exposure to MLOps techniques (e.g., fine-tuning pipelines, model hosting)
  • Experience mentoring other engineers or working closely with design

Skills

TypeScriptNode.jsReactLLMsRAGVector DatabasesPrompt EngineeringPostgresMLOpsJavaScript

Similar roles

ML Engineering jobs
Baseten

Software Engineer - Voice AI (Inference Runtime)

BasetenSan Francisco, CA +1

Build and own high-performance inference runtime for Voice AI models including STT, TTS, and voice agents. Design real-time systems with low tail latency, collaborate cross-team, and optimize model serving for production workloads. Requires CS degree and real-time systems experience.

165k – 330k/yr
HybridML Engineering
Deepgram

Forward Deployed Engineer, Deepgram for Restaurants

DeepgramNew York, NY

Deploys and integrates Deepgram’s voice AI platform into enterprise restaurant environments, owning technical implementations, customizations, production support, and feedback to product teams. Requires strong software engineering skills across APIs, SDKs, cloud infra, and customer obsession.

165k – 220k/yr
RemoteML Engineering
Tabs

Software Engineer, AI/ML

TabsNew York, NY

Build full stack AI/ML features for finance automation platform, owning greenfield projects with Python/TypeScript/Next.js. Requires 3-5 years full stack exp, 1+ year AI/ML inference, in-person NYC.

165k – 225k/yr
On-site3+ YOEML Engineering
LangChain

Fullstack Software Engineer, Applied AI

LangChainNew York, NY +2

Builds and deploys production-grade AI agents and workflows for business functions like marketing, recruiting, and product. Requires 3+ years experience shipping AI/ML apps, including LLM systems, with strong Python/TypeScript skills.

165k – 190k/yr
On-site3+ YOEML Engineering
Baseten

Software Engineer - Training Infrastructure

BasetenSan Francisco, CA +1

Architects and leads development of scalable ML training infrastructure, including scheduling, storage, networking, and reinforcement learning systems. Requires proficiency in Go, Kubernetes expertise, distributed systems knowledge, and experience with cloud providers and ML workloads.

165k – 330k/yr
HybridML Engineering