AI Engineer

About Bizmoni Corp. Bizmoni is building an AI Business Network designed to help people and businesses connect, earn, learn, and grow in the AI era. As a seed-stage, pre-revenue company, we are strengthening our platform, growing our global ecosystem, and laying the foundations for future funding and scale.

This is an opportunity to join an entrepreneurial, international team and help shape both the product and the business.

About the Role

Architecture and platform build Design and build our LLM infrastructure from scratch: model serving, orchestration, data pipelines, vector storage and observability.

Make and document key build-vs-buy decisions, including hosted APIs (OpenAI, Anthropic, Google) versus self-hosted open-weight models (Llama, Mistral, Qwen). Stand up scalable, cost-efficient inference using tools such as vLLM, TGI or Triton, on GPU and CPU infrastructure.

Build the cloud foundations on [AWS / Azure / GCP] using infrastructure-as-code (Terraform or similar), Docker and Kubernetes. LLM application engineering Build retrieval-augmented generation (RAG) pipelines: ingestion, chunking, embeddings, hybrid search and re-ranking.

Develop agentic workflows, tool use and function calling for production use cases. Fine-tune and adapt models where it adds value (LoRA/QLoRA, PEFT), and know when prompting or retrieval is the better answer. Expose AI capabilities through well-designed Python APIs (FastAPI or similar) for product and engineering teams.

Quality, reliability and safety Build evaluation frameworks to measure accuracy, hallucination, latency and cost, and use them to gate releases. Implement monitoring, tracing and alerting for LLM services (e. g. LangSmith, Langfuse, OpenTelemetry, Prometheus/Grafana).

Put guardrails in place for data privacy, prompt injection, PII handling and GDPR compliance. Own CI/CD and MLOps practices for models, prompts and pipelines. Leadership and collaboration Set coding standards, write clear technical documentation and revie