Position Summary, Responsibilities and Expectations:
Own AI/ML feature development across multiple platforms, end to end.
Handle model integration, including choosing and swapping providers as needs change.
Build and maintain LLM pipelines and orchestration logic.
Set up retrieval systems and the data logic that feeds them.
Run evaluation on model output and iterate to improve accuracy, reliability and cost.
Optimize performance, including cost and latency trade-offs in production.
Track emerging AI tools and frameworks and bring in what's worth adopting.
Essential Skills and Experience
4+ years of
software engineering experience.
Strong Python skills.
Production experience with LLMs.
Experience with vector stores and retrieval-augmented generation.
Experience with agentic frameworks.
Practical MLOps experience, including deploying and monitoring AI systems in production.
A working grasp of cost and latency trade-offs when running LLM-based systems at scale.
Comfortable working alongside a small core engineering team.
Fluent English, both in written and speaking.