52 new jobs

Job overview and responsibility

Most agentic AI work optimizes against benchmarks that don't push back. Here, the agent's hypotheses get tested at the bench — its reasoning is answerable to real experimental results, not a leaderboard. We have a working system orchestrating 300+ tools; what we need is someone to keep it at the frontier. You'll read the latest in agentic research, decide what's real, and ship it into a system where "better" means a better experiment runs next week. If you want your work on autonomous agents to be grounded in reality instead of demos, this is the rare seat where it is. - Own the research-to-production loop for our agent: survey emerging agentic techniques, run structured experiments against them, and ship what proves out. - Continuously upgrade core agent capabilities — planning, tool selection and reasoning, memory, multi-agent coordination — measured against real benchmarks, not demos. - Build and own the evaluation harness that tells us whether a change is actually an improvement. This is the backbone of the role. - Diagnose where the agent fails at the frontier of its current capability and design the fixes. - Set technical direction for agentic best practices internally; review, mentor, and raise the quality bar for the existing engineers. - Translate latest research into pragmatic engineering decisions under real reliability and cost constraints.

Required skills and experiences

- 6+ years software/ML engineering, with a recent track record building production agentic systems (planning, tool use, multi-step reasoning) — not prompt pipelines. - Demonstrated ability to take a technique from current research and land it in a production system, with measured impact. - Strong command of agent frameworks and patterns (e.g., LangGraph, MCP, or equivalents) and the internals: tool definition, state/context management, orchestration. - Rigorous evaluation — you’ve designed eval harnesses for non-deterministic systems and trust data over intuition. - Fluent in reading and dismantling ML/agent papers; strong Python and system-design fundamentals.

Preferred skills and experiences

- Exposure to scientific or research workflows, ideally drug discovery or other iterative experimental loops. - Experience mentoring or setting technical direction for a small team. - Background in RAG, memory systems, or multi-agent orchestration; bio/chem familiarity a plus.

Why Candidate should apply this position

- Competitive salary - Workplace: This role is based in our Hanoi office, located in the vibrant Old Quarter (Mon - Fri) - Build a professional network through collaborations with pharmaceutical companies, industry leaders, and academic experts. - Work on impactful projects that address critical challenges in drug discovery and healthcare.

Report to

CEO

Interview process

Screening -> 1-2 rounds of interview