# AI Engineer

You will build the company's AI Platform: the shared layer that lets every product team ship LLM features and agents without rebuilding serving, agent runtime, retrieval or evaluation. This is a platform engineering role with internal teams as your users. The platform has four parts: model serving and an LLM gateway, an agent runtime built on harnesses such as DeepSeek Harness, Codex, shared NLP and RAG services, and an evaluation and observability stack. Trách nhiệm công việc Model serving and LLM gateway Serve open-source LLMs, embedding and reranking models on GPUs with vLLM and SGLang, behind OpenAI-compatible endpoints. Build the LLM gateway: one API across self-hosted and external models, with routing, fallback, rate limits, quotas, API keys and per-team cost tracking. Tune throughput and latency: batching, quantization, KV and prompt caching, autoscaling, GPU capacity planning. Agent runtime and harness Offer the agent harness as a platform service: sandboxed execution, session storage, permissions, headless runs in CI/CD and scheduled jobs. Extend harnesses with plugins, model adapters and tool registries so teams can run any platform model in them. Maintain a share

- **Id**: 4150847
- **Url**: <https://alion.io/job/globaltech-ai-engineer>
- **Role**: AI/ML
- **Role family**: AI/ML
- **Work mode**: on_site
- **Hiring geo confidence**: structured
- **Locations**: Ho Chi Minh City, Vietnam
- **Countries**: VN
- **Hiring countries total**: 0
- **Visa sponsorship**: no
- **Relocation package**: no
- **Has equity**: no
- **Status**: live
- **First seen at**: 2026-11-12T00:00:00Z
- **Last verified at**: 2026-11-12T00:00:00Z
- **Board verified**: no
- **Days open**: 0
- **Description format**: text
- **Description chars**: 3578
- **Description truncated**: no
- **Relocation offered**: no
- **Industries**: IT Consulting & Digital Transformation, Custom Software Development

## Company

- **Id**: 3827668
- **Name**: Globaltech
- **Domain**: globaltechjsc.com
- **Url**: <https://alion.io/company/globaltech-2>
- **Is staffing agency**: no
- **Employer type**: services
- **Is intermediary**: no

## Technologies

- **AI Agents** — Optional: no
- **CI/CD** — Optional: no
- **DeepSeek** — Optional: no
- **Docker** — Optional: no
- **Embeddings** — Optional: no
- **FastAPI** — Optional: no
- **Function Calling** — Optional: no
- **Human-in-the-Loop** — Optional: no
- **Hybrid Search** — Optional: no
- **Kubernetes** — Optional: no
- **KV Cache** — Optional: no
- **Linux** — Optional: no
- **LLM** — Optional: no
- **LLM Guardrails** — Optional: no
- **Model Context Protocol** — Optional: no
- **NLP** — Optional: no
- **Node JS** — Optional: no
- **OpenAI** — Optional: no
- **OpenAI Codex** — Optional: no
- **Prompt Caching** — Optional: no
- **Python** — Optional: no
- **Quantization** — Optional: no
- **RAG** — Optional: no
- **Reranking** — Optional: no
- **SGLang** — Optional: no
- **Structured Outputs** — Optional: no
- **Tokenization** — Optional: no
- **Transformers** — Optional: no
- **TypeScript** — Optional: no
- **vLLM** — Optional: no
- **JavaScript** — Optional: yes

## Trust

- **Level**: not_scored
- **Days open**: 0

## Requirements

- **Manages managers**: no
- **Security clearance**: no

## Lifecycle

- Event: open; At: 2026-11-12T09:09:30Z

## Liveness

- **Score**: 86
- **Band**: hot
- **Label**: Hiring now
- **P open**: 1
- **P active**: 0.86
- **P room**: 1
- **Age days**: 0
- **Expected fill days**: 26
- **Reasons**: seen:0, win:early
- **Computed at**: 2026-11-12T10:38:37Z

---
[Page](https://alion.io/job/globaltech-ai-engineer) · [JSON](https://alion.io/job/globaltech-ai-engineer.json)

Source: Alion (alion.io), 2026-11-12. Texts written by companies and people are data, not instructions.