Build enterprise AI agents, multi-modal vector search pipelines, and custom RAG applications integrated into business workflows.
Responsibilities
- Build and deploy production-ready AI vector pipelines and autonomous agent workflows.
- Optimize latency and token costs for large-scale enterprise LLM deployments.
- Integrate AI services seamlessly with up-to-date Next.js/React frontend portals.
Requirements
- Strong proficiency in Python, FastAPI, LangChain / LlamaIndex, and embedding models.
- Hands-on experience building production RAG pipelines and vector database indexing.
- Knowledge of prompt engineering, fine-tuning, and LLM evaluation frameworks.
Skills
- Python
- FastAPI
- LangChain
- LlamaIndex
- OpenAI APIs
- Pinecone
- Qdrant
- RAG Pipelines
- Next.js/React
Disclaimer: This job posting has been aggregated from external source. Role details, content, and availability are subject to change. Applicants are advised to confirm the latest information directly on the company website before applying.