Senior Lead, AI Engineering — LLM & GenAI Systems

Zs Associates; Bellevue, Northern (WA, KY); Hybrid; USD 180,000 - 240,000; Full time

Benefits offered by this job

Hybrid work model

Travel opportunities

Job summary

ZS is seeking a highly motivated Applied AI Engineer with a deep interest in Large Language Models (LLMs) to build, optimize, and evaluate production-grade LLM systems. The role focuses on RAG pipelines, fine-tuning workflows, and scalable inference, with a strong emphasis on Python, FastAPI, and modern ML tooling.

Ideal candidates will have 4+ years in ML with production LLMs, experience in NLP/vision, and a client-first mindset.

Qualifications

• Master's or Bachelor's in Computer Science or related field.
• 4+ years of hands-on ML experience with production LLM systems.
• Strong fundamentals in ML, DL and fine-tuning (LLM).
• Experience with backend API design (FastAPI) and async patterns.
• Experience with vector databases and embedding search.

Responsibilities

• Design and implement LLM-powered applications using state-of-the-art transformer models.
• Build and optimize RAG pipelines using embeddings, chunking strategies, and vector search.
• Experiment with prompt engineering, structured outputs (JSON schemas/function calling), and tool-augmented LLMs (agents/workflows).
• Fine-tune models using LoRA, PEFT, and instruction tuning.
• Develop and evaluate embedding models for similarity search and semantic retrieval.
• Conduct LLM evaluation using automated and human-in-the-loop techniques.

Skills

Python

FastAPI

Async programming

Type hints

Pydantic

SOLID principles

Langfuse

ML Ops

NLP

English fluency

LLM systems

Education

Bachelor's degree in Computer Science

Tools

Pinecone

Weaviate

Chroma

Job description

ZS is seeking a highly motivated Applied AI Engineer with a deep interest in Large Language Models (LLMs) to build, optimize, and evaluate production-grade LLM systems. The role focuses on RAG pipelines, fine-tuning workflows, and scalable inference, with a strong emphasis on Python, FastAPI, and modern ML tooling.

Ideal candidates will have 4+ years in ML with production LLMs, experience in NLP/vision, and a client-first mindset.