Senior Agentic AI Evaluation Engineer

RESARO SINGAPORE PTE. LTD.; Singapore; On-site; SGD 120,000 - 180,000; Full time

Job summary

Resaro Singapore Pte. Ltd. is seeking a senior engineer to own the agentic AI evaluation engine for the Approved Intelligence Platform (AIP). You will assess tool-using, multi-step agents for safe deployment, pushing the boundaries of governance and reproducibility in high-stakes settings.

You’ll work hands-on on a growing product, collaborating with product and governance teams to formalize evaluation logic and ensure reliability across Singapore and Europe teams.

Qualifications

• 5+ years of professional software engineering experience shipping and operating production systems in Python.
• Demonstrated depth in agentic AI with building, orchestrating, or evaluation of LLM agents.
• Understanding of tool-calling, memory, and multi-step control flow beyond tutorials.
• Knowledge of standard benchmarks and why benchmarks may overstate production reliability.
• Ability to scope ambiguous problems and drive to shipped, tested outcomes.

Responsibilities

• Own the agentic-evaluation engine and score agents on relevant metrics.
• Evaluate stateful, multi-turn behaviour across sessions.
• Design for evaluator integrity: isolate runner from agent and audit ground truth.
• Build agentic-security surface with red-teaming and adversarial evaluation.
• Close the lab-to-production gap with deployment-focused evaluations.
• Translate governance requirements (EU AI Act, NIST RMF, ISO 42001) into tests.
• Set the technical bar through spikes, ADRs, and code reviews.
• Extend evaluation to embodied/autonomous systems as needed.

Skills

Python

Agentic AI

LLM Agents

Tool-calling

Memory Management

Multi-turn Evaluation

Interoperability

Tools

Kubernetes

Nuclio

Parquet

Iceberg

DuckDB

Job description

Resaro Singapore Pte. Ltd. is seeking a senior engineer to own the agentic AI evaluation engine for the Approved Intelligence Platform (AIP). You will assess tool-using, multi-step agents for safe deployment, pushing the boundaries of governance and reproducibility in high-stakes settings.

You’ll work hands-on on a growing product, collaborating with product and governance teams to formalize evaluation logic and ensure reliability across Singapore and Europe teams.