Lead AI Engineer

Zs Associates; Bellevue (WA); On-site; USD 120,000 - 150,000; Full time

Benefits offered by this job

Comprehensive total rewards package

Robust skills-building programs

Multiple career progression paths

Job summary

A leading management consulting firm in Bellevue, WA is seeking an Applied AI Engineer focused on creating LLM systems. The ideal candidate will possess a strong background in machine learning and experience with transformer models. Ideal applicants should have over 4 years of experience in ML, proficiency in Python programming, and familiarity with backend API design. Join a collaborative culture that promotes professional development and impactful work in AI solutions.

Qualifications

• 4+ years' hands-on experience with production LLM systems.
• Strong understanding of transformer architectures.
• Experience in working with NLP & computer vision.

Responsibilities

• Design and implement LLM-powered applications.
• Build and optimize RAG pipelines.
• Develop and evaluate embedding models for similarity search.

Skills

Machine Learning

Programming in Python

Prompt Engineering

Backend API Design

Client-first mentality

Education

Bachelor's or Master's degree in Computer Science

Tools

FastAPI

MLFlow

Pinecone

Langfuse

Job description

ZS is a place where passion changes lives. As a management consulting and technology firm focused on improving life and how we live it, we transform ideas into impact by bringing together data, science, technology and human ingenuity to deliver better outcomes for all. Here you’ll work side‑by‑side with a powerful collective of thinkers and experts shaping life‑changing solutions for patients, caregivers and consumers worldwide. ZSers drive impact by bringing a client‑first mentality to each and every engagement. We partner collaboratively with our clients to develop custom solutions and technology products that create value and deliver company results across critical areas of their business. Bring your curiosity for learning, bold ideas, courage and passion to drive life‑changing impact to ZS.

What you’ll do:

We are seeking a highly motivated Applied AI Engineer with a strong foundation in Machine Learning and a deep interest in Large Language Models (LLMs) and Generative AI. This role focuses on building, optimizing, and evaluating production‑grade LLM systems, including Retrieval‑Augmented Generation (RAG), fine‑tuning workflows, and scalable inference pipelines.

• 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 techniques such as 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 (offline + online).
• Optimize inference workflows for latency, GPU utilization, and cost efficiency (quantization, batching, caching).
• Build and maintain REST API Services (FastAPI etc.) to deploy LLM/RAG endpoints, integrate with product systems, and support scalable inference.
• Contribute to integration of AI systems into production software environments (CI/CD, monitoring, reliability).
• Research and prototype cutting‑edge approaches in Generative AI and share learnings with the team.

What you’ll bring:

• A master's or bachelor's degree in Computer Science or related field from a top university
• 4+ years' hands‑on experience in Machine Learning (ML) with production LLM systems
• Good fundamentals of machine learning, deep learning and fine tuning models (LLM) including:
  • Understanding of transformer architectures
  • Prompt engineering expertise
  • Embeddings and vector search
• Experienced in backend API design with FastAPI, async patterns, rate limiting
• Experience with vector DB including:
  • Pinecone, Weaviate, or Chroma
  • Embedding storage and similarity search
  • Hybrid search implementations
• Strong programming expertise in Python is must including:
  • Async programming (asyncio, async/await)
  • Type hints and Pydantic
  • SOLID principles and design patterns
• Experience in ML Ops to measure and track model performance including:
  • MLFlow for model tracking
  • Langfuse for LLM observability (strongly preferred)
  • Model versioning and A/B testing
• Experience in working with NLP & computer vision
• Fluency in English
• Client‑first mentality
• Intense work ethic
• Collaborative spirit and problem‑solving approach

At ZS, your growth matters. We offer a comprehensive total rewards package that supports your health and well‑being, financial future, time away, and professional development. With robust skills‑building programs, multiple career progression paths, internal mobility, and a deeply collaborative culture, you’ll have the opportunity to do meaningful work, expand your capabilities, and thrive as part of a global community. For details on total rewards in United States, visit ZS US office locations | Where we work | ZS.