Senior Applied AI Engineer (LLM)

Location: Hybrid in New York City; the role is also described as full-time and in-person

Salary: $200,000–$240,000 annually, plus bonus and early-stage equity

Company

hirify.global is building an AI-native primary intelligence platform for enterprises, investment firms, and asset managers, automating expert research from study design and recruitment through AI-moderated interviews and insight synthesis.

What you will do

• Own the LLM orchestration layer powering real-time, multi-turn expert interviews for the AI Moderator.
• Design prompts, context handling, model routing, latency optimization, evaluations, monitoring, and production guardrails.
• Build Python and TypeScript APIs and microservices that transform interview data into structured, queryable customer insights.
• Improve retrieval relevance and downstream LLM processing through labeled data, evaluation, prompt, and code iterations.
• Partner with research, product, data engineering, and the founding team to develop AI-powered research assets and decide what to build or buy.
• Help architect an MCP over proprietary data and the tools used by the orchestration layer.

Requirements

• 5+ years of experience building and shipping applied AI/ML systems in production.
• Hands-on LLM experience with prompt and system design, retrieval-augmented generation, tool or function calling, and structured outputs across multiple model providers.
• Strong backend engineering skills in Python and TypeScript, including API and microservice development.
• Experience with vector databases, search, and optimizing retrieval quality and latency at scale.
• Ability to work with unstructured data such as audio, transcripts, and financial documents, including ingestion and transformation pipelines.
• Strong ownership, with the ability to take systems from prototype to production without a detailed specification.

Nice to have

• Applied AI/ML engineering experience at a technology startup.
• Experience with production agentic or multi-turn voice or chat systems.
• Experience building evaluation frameworks, including offline and online evaluations, LLM-as-judge, and regression testing.
• Familiarity with speech-to-text models such as Deepgram, AssemblyAI, or Whisper.
• ETL and data engineering experience, or a background in fintech, research, or another AI-driven, data-intensive startup.

Culture & Benefits

• Competitive base salary, bonus, and a meaningful early-stage equity grant.
• Health coverage, flexible PTO, and paid holidays.
• High-velocity environment with high standards, high agency, and substantial ownership.
• Small founding team building processes, playbooks, and systems for a growing AI company.
• Collaborative environment focused on ambitious work and enjoyment of working together.