INTRODUCTION
Phenikaa-X is a Phenikaa Group company developing autonomous vehicles, robotics and automation technology in Vietnam. Our portfolio includes autonomous vehicles, autonomous mobile robots and drones, supported by technologies such as artificial intelligence, mapping and simulation. We aim to bring autonomous technology into transportation, manufacturing and service operations, with a focus on safety, reliability and operational efficiency.
This role develops learned driving policies that connect multimodal observations, vehicle state, route context and, where applicable, language instructions to actions or trajectories. You will work with research, planning, controls and integration colleagues to turn model improvements into reproducible evidence and integration-ready artifacts. Own a well-defined model development workstream, from data preparation to evaluation and a reproducible handoff, for end-to-end driving or vision-language-action (VLA) policies.
JOB DESCRIPTION
- Define policy targets, action representations and success criteria with planning and controls colleagues; turn an ambiguous behavior problem into a testable model plan.
- Lead data curation and model training or adaptation; choose methods through controlled comparisons and prevent temporal, geographic and sequence-level evaluation leakage.
- Build scenario-based offline and closed-loop evaluations; diagnose compounding errors, instruction failures and regressions, and document what the evidence does and does not establish.
- Resolve trade-offs between behavior, compute and timing; agree on output validity checks, stale-action handling and fallback interfaces with controls and integration teams.
- Own reproducible model releases and integration acceptance evidence within the workstream; mentor engineers, coordinate defect resolution and communicate remaining limitations.
REQUIREMENTS
- A bachelor’s degree in a relevant technical field, or equivalent practical experience; demonstrated ownership of substantial ML development work.
- A track record of independently delivering a policy or multimodal model from data design through evaluation and integration, with clear evidence of your technical decisions and impact.
- Strong Python and deep learning skills, including sequence models, imitation learning and practical adaptation of a VLM or learned embodied policy.
- Experience evaluating policies in closed-loop simulation or a comparable robotics system and explaining why offline prediction metrics can miss behavioral failures.
- Ability to diagnose training, data and runtime failures; design controlled experiments; and evaluate latency, observation age, model state and deployment constraints together.
- Experience leading a technical workstream, reviewing engineering work and coordinating with partner teams; ability to document decisions and discuss technical material in English.
Preferred skills
- Experience integrating E2E/VLA policies on physical robots or vehicles under controlled validation procedures.
- Experience with reinforcement learning, world models, distributed training, distillation or on-device model optimization.
- Relevant publications, open-source contributions or reusable evaluation tooling with a clear account of your contribution.
BENEFITS
- Salary: negotiation based on candidate’s capacity.
- Lunch allowance, holiday bonuses, 13th-month salary.
- Birthday, sick leave, maternity, and welfare policies according to Vietnam Labor Code.
- Overtime pay in accordance with legal regulations (150–300% rate depending on time).
- Full social insurance contribution; private health insurance for employees and managers.
- Dynamic, friendly working environment with passionate and talented engineers.
- Equipped with modern equipment such as a high configuration PC.
- Accessed high-configured supercomputers for training AI models.
CONTACT
Recruitment Department – Phenikaa-X JSC
- Email: tuyendung@phenikaa-x.com
- Contact: 0971131001 (Ms. Thuy Duong)