Ditto AI is hiring a Founding AI Engineer to build the core AI systems that power our social networking platform. You will report directly to the cofounders and collaborate closely with product and engineering in an early, high-ownership role with a team of less than 10 people. Your work will bring our smartest matchmaking AI to life, design chat agents that feel human, and create the internal tools that other AIs use to reason, retrieve, and act.

What You'll Do

Ship agentic matchmaking from research to production—own the end-to-end loop (retrieval, reasoning, tool use, safety) and drive measurable accuracy improvements.
Build a prompt and model evaluation harness (offline and online) to compare prompts, models, and policies, support A/B testing, and enable fast iteration.
Optimize AI chat systems for lower latency, higher perceived human-likeness, and more consistent outcomes across providers.
Design and maintain context engineering pipelines (RAG, memory, summarization, compression, grounding) for conversations and matchmaking.
Stand up observability for agents (traces, costs, failures, hallucinations, guardrails) and create dashboards that guide product decisions.
Collaborate daily with the cofounders and product to translate user problems into agent behaviors, experiments, and shipped features.
Write clear, maintainable code; create small internal tools and SDKs other engineers and AIs will use.

What We're Looking For

2–4+ years of relevant experience or a standout personal portfolio of agents and LLM apps—show us what you've built.
Strong programming foundations in data structures, algorithms, testing, and profiling.
Proficiency in TypeScript for product code, tools, and services, and Python for model operations, evaluations, and data.
Experience building with multiple LLM providers and tool-calling or function-calling; comfortable swapping models and orchestrating fallbacks.
Hands-on experience with RAG (indexing, chunking, embeddings, reranking) and context engineering for reliability and cost/latency trade-offs.
Practical prompt engineering skills and prompt libraries; ability to reason about failure modes and systematically improve prompts and policies.
Ability to define metrics and KPIs (accuracy, latency, cost, safety), run A/B tests, and loop in human feedback for quality.
Comfortable using MongoDB in a production environment.
Builder's mindset: thrives with ambiguity, ships quickly, debugs systematically, and sweats the user experience.

Nice to Have

Familiarity with vector databases (e.g., pgvector, Redis, Pinecone, Weaviate).
Experience with MCP (Model Context Protocol).
Experience with agent frameworks (LangGraph, CrewAI, Assistants).
Experience with LLM observability and evaluation tools (e.g., Langfuse, Promptfoo, Ragas, TruLens).
Experience with retrieval and embeddings.
Experience with safety, guardrails, or red-teaming.

Technical Stack

Languages: TypeScript, Python
Databases: MongoDB
AI Systems: LLM providers, RAG systems
Infrastructure: Vector databases

Team & Environment

You'll be joining a team of less than 10 people in an early, high-ownership role, reporting directly to the cofounders. The culture is young and passionate, focused on building the future of social networking by combining cutting-edge AI technology with thoughtful design to create experiences that genuinely improve how people connect.