Senior Software Engineer – AI & LLM (12‑month contract, up to SGD12k)

About the role

We are looking for a Senior Software Engineer to lead our AI Evaluation Infrastructure (EvalsHub) and embed with AI product teams. You will design, build, and scale pipelines, observability tools, and automation that keep our LLM agents accurate, cost‑effective, and reliable at scale.

Key responsibilities

• Own and scale EvalsHub backend, SDK, CLI, and frontend components.
• Develop golden datasets, regression pipelines, and CI/CD integration for model releases.
• Automate human‑review processes using LLM‑as‑judge, multi‑turn, and deterministic evaluators.
• Instrument distributed Go and Python services with OpenTelemetry and Temporal workflows for full traceability.
• Run experiments on model architectures, RAG, and embeddings to optimise accuracy, latency, and cloud cost.
• Write technical documentation, lead tool migrations, and participate in LLMOps production rotation.

Required profile

• Bachelor's degree in Computer Science or a related field.
• Minimum 2 + years of software engineering experience.
• Hands‑on experience with LangSmith, LangChain/LangGraph, FastAPI, or Temporal.
• Proven work on LLM‑as‑judge frameworks, agent‑trajectory analysis, RAG, or Text‑to‑SQL.
• Strong analytical skills with geospatial data handling.

Required skills

• Go
• Python
• OpenTelemetry
• Temporal
• LangSmith
• LangChain / LangGraph
• FastAPI
• React
• TypeScript
• Grafana
• Redis