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.

Bachelor's degree in Computer Science, Artificial Intelligence, Applied Mathematics or equivalent. 2+ years of NLP/LLM experience, including at least one LLM or agent system running in production. Experience building shared services or internal platforms used by other teams: API design, multi-tenancy, versioning, SLAs.

Experience serving LLMs with vLLM or SG

Lang: deploying OpenAI-compatible endpoints on GPUs, tuning batching, quantization and KV cache, and benchmarking throughput and latency. Strong Python and backend skills (FastAPI or similar, async, queues); reading and writing TypeScript/Node.js is a big advantage, since many harnesses are written in TypeScript. Solid understanding of how agents work: agent loop, tool calling, context window management, prompt caching, structured output.

Hands-on with at least one agent harness or coding agent (DeepSeek Harness, Codex or similar) at the customization level, not only as an end user. Experience building RAG and working with vector databases. Strong NLP fundamentals: Tran