18 days ago
Base Salary
$200k - $240k/yr
Responsibilities
- Own the real-time, multi-turn LLM orchestration layer for the AI Moderator, including prompt and context design, model routing, and latency optimization.
- Build production evals, monitoring, and guardrails so AI quality issues are identified before reaching customers.
- Develop production APIs and services that convert interview data into structured, queryable customer insights.
- Partner with product, data engineering, research, and the founding team to ship AI-powered research assets and define the retrieval and generation stack.
- Improve retrieval relevance and downstream LLM processing through labeled data, evaluation, prompt or code iteration, and re-evaluation.
- Help architect an MCP and the tools supporting the AI orchestration layer.
Requirements
- 5+ years of experience building and shipping applied AI/ML systems in production, ideally including startup experience.
- Deep hands-on experience with LLM prompt and system design, retrieval-augmented generation, tool or function calling, and structured outputs across multiple model providers.
- Strong backend engineering skills in Python or TypeScript, including designing and shipping APIs and microservices.
- Experience with vector databases, search, and optimizing retrieval quality and latency at scale.
- Comfort working with unstructured data such as audio, transcripts, and financial documents and building pipelines that make it model-ready.
- Ability to take problems from prototype through production with a high degree of ownership.
- Preferred experience with agentic or multi-turn conversational systems, production evaluation frameworks, speech-to-text models, ETL and data engineering, and fintech, research, or AI-driven data-intensive startups.
- Preferred familiarity with Deepgram, AssemblyAI, Whisper, or similar speech-to-text systems.
Benefits
- Competitive base salary plus bonus; compensation amount is not specified.
- Meaningful early-stage equity grant tied to company growth.
- Health coverage, flexible paid time off, and paid holidays.
- Full-time, in-person work in New York City.
Tech Stack
Categories
