Senior AI Developer

We’re building  production-grade LLM / AI capabilities  into our Cloud Operating System and we need someone who can ship. If you like taking AI from prototype → scalable product, this is for you.

What you’ll do

Design and ship AI / LLM features that run in production

Build RAG-style systems (embeddings, vector search) that actually perform

Own model serving, observability, and reliability across our AI stack

What we’re looking for

Strong Go (Golang)  for production ML services

LLMs, RAG, embeddings, vector search  (FAISS / pgvector)

PyTorch or TensorFlow  and experience with  model serving / inference

MLOps : CI / CD, monitoring, evaluations, Docker / Kubernetes, GPUs

Inference engine experience :  e.g.  vLLM, SGLang, TensorRT, Triton  or similar high-performance serving stacks

Nice to have

LangChain / LlamaIndex

Triton Inference Server (if not above)

Kafka / streaming

Privacy & security in ML

Experience with OpenAI / Hugging Face ecosystem

Location :  Remote

Type :  Full-time

If you’re passionate about turning AI research into  reliable, scalable product features , let’s talk.

Send your resume to  career@piovation.com