Senior AI/ML Engineer: LLMs, RAG & Production

EvolutionIQ; New York, Northern (NY, KY); Hybrid; USD 200,000 - 235,000; Full time

Benefits offered by this job

Annual bonus

RSU equity

Medical, dental, vision

Job summary

EvolutionIQ in New York, NY, is seeking an experienced AI/ML Engineer to lead end-to-end development of our medical synthesis product. You will architect large‑scale AI/ML systems, balance performance and reliability, and push the boundaries of LLM‑driven features in production.

You’ll collaborate with Product, Engineering, SMEs, and data labelers to improve model outputs, implement RAG with embeddings, and ensure robust extraction from complex medical documents while maintaining a strong focus

Qualifications

• 5-8+ years of experience writing performant Python code.
• Minimum 1 year of experience building and deploying products powered by large language models (LLMs).
• Proven experience leading technical projects from concept through production deployment.
• Experience making architectural decisions for AI/ML systems.

Responsibilities

• Lead AI/ML projects end-to-end, from ideation to deployment and optimization.
• Design, build, and deploy AI-powered features for our claim synthesis product.
• Develop hybrid ML solutions using LLMs, RAG, embeddings, and vector search.
• Write clean, scalable code and improve performance of AI/ML systems in production.
• Collaborate with SMEs and cross-functional teams to refine requirements and drive results.

Skills

Python

LLMs

RAG

Vector search

API services

Architectural decisions

Prompt engineering

Tools

Vector search

Service-oriented architecture

Job description

EvolutionIQ in New York, NY, is seeking an experienced AI/ML Engineer to lead end-to-end development of our medical synthesis product. You will architect large‑scale AI/ML systems, balance performance and reliability, and push the boundaries of LLM‑driven features in production.

You’ll collaborate with Product, Engineering, SMEs, and data labelers to improve model outputs, implement RAG with embeddings, and ensure robust extraction from complex medical documents while maintaining a strong focus