Senior AI Engineer

Weblink Solutions; United States; Remote; USD 140,000 - 230,000; Full time

Job summary

Weblink Solutions is seeking an experienced engineering leader to drive production AI workflow projects across multiple clients, from discovery and design to deployment and ongoing monitoring. You will balance hands-on development with architectural decisions, production support, and mentoring junior engineers.

The role emphasizes Python, asynchronous programming, and modern AI tooling, with responsibilities spanning logging, tracing, and evaluation.

Qualifications

• 5+ years software engineering experience.
• 2+ years AI/ML or LLM systems experience.
• Production experience with major LLM provider or self-hosted models.
• Strong Python with async, typing, testing, packaging.
• Experience with FastAPI, Pydantic, LangChain or LlamaIndex.
• Familiarity with workflow tools and vector DBs.

Responsibilities

• Lead production AI workflow projects from discovery to launch.
• Design and build AI systems using workflow automation and Python services.
• Choose between existing tools, custom code, or fine-tuning for needs.
• Add logging, tracing, drift detection, cost tracking, alerts.
• Diagnose model behavior, data quality, and integrations.
• Review code/architecture and mentor junior engineers.

Skills

Python

AI/ML

LLM systems

Async programming

Type hints

Testing

Packaging

Documentation

Mentoring

Tools

FastAPI

Pydantic

LangChain

LlamaIndex

n8n

Make

Zapier

Temporal

pgvector

Pinecone

Qdrant

Weaviate

Job description

Role overview

Lead production AI workflow projects for several clients at a time, taking each from discovery and system design through implementation, launch, and ongoing monitoring. The work combines hands-on engineering with architectural decisions, production support, and mentoring junior engineers.

Responsibilities

• Design and build AI systems using workflow automation, Python services, and large language model APIs.
• Choose when to use existing workflow tools, custom code, or model fine-tuning to meet project needs.
• Add logging, tracing, drift detection, cost tracking, and alerts to production workflows.
• Diagnose issues involving model behavior, integrations, and data quality.
• Review code and architecture, and mentor junior engineers through regular one-to-ones.
• Improve shared workflow components, evaluation tools, and prompt libraries.

Requirements

• At least five years of software engineering experience, including two or more years with AI, machine learning, or LLM-powered systems.
• Production experience with a major LLM provider or self-hosted open-source models.
• Strong Python skills, including asynchronous programming, type hints, testing, and package management; familiarity with a framework such as FastAPI, Pydantic, LangChain, or LlamaIndex.
• Experience with workflow tools such as n8n, Make, Zapier, or Temporal, and sound judgment about when to use them.
• Experience with embeddings and vector databases such as pgvector, Pinecone, Qdrant, or Weaviate.
• Ability to evaluate and troubleshoot variable model outputs using techniques such as prompt design, evaluation harnesses, or A/B testing.
• Clear written communication for architecture documents, incident reviews, and client reports.