Back
Remote mid-level LLM role with broad full-stack and observability requirements, leading to moderate competition.
Highly specialized LLM agent engineering skills limit transferability outside AI-first product teams.
Multiple explicit years and mandatory production LLM/backend experience create stringent shortlisting filters.
Login to See Your Match Score
Create a free account or log in to unlock your CV match score across:
Build and evolve production AI agents on foundation models like AWS Bedrock, focusing on orchestration, context engineering, evaluation pipelines, and monitoring.
Develop and maintain production observability and tracing for LLM and agent systems with measurable deliverables starting immediately.
Collaborate as the first dedicated AI-agent engineer alongside the AI function lead and a full stack engineer, influencing agent architecture decisions and production frameworks.
2+ years of production experience building LLM agents with tool-calling, streaming, context management, and orchestration frameworks (LangChain, LangGraph or custom).
1.5+ years experience with evaluation-driven development of evaluation datasets and pipelines for LLM tools.
1+ year hands-on experience with LLM observability, tracing, and instrumentation (Langfuse strongly preferred, OpenTelemetry acceptable).
5+ years backend engineering including TypeScript/Node, Postgres, serverless AWS; proven ability to ship agentic AI systems end-to-end.
Deep experience operating production LLM agents with strong agent architecture fundamentals and troubleshooting of concrete failure modes.
Proven ability to deliver on roadmap timelines independently as an individual contributor in a small, remote product team.
Experience with LLM cost optimisation, observability, and evaluation pipelines indicating strong domain expertise beyond typical ML engineering.