Access Control, CPU (Central Processing Unit), Docker, Enterprise Protection, Go Programming Language (Golang), Metadata, Open Source, Open Source Databases, Performance Modeling, Performance Tuning/Optimization, Prototyping, Python Programming/Scripting Language, Software Development, Software Engineering
Core Experience
- Hands-on experience deploying open-source LLMs such as Meta Llama 3 and Mistral / Mixtral in on-prem or private environments (25%)
- Strong proficiency in Python for LLM inference, prompt engineering, and integration (25%)
- Experience with CPU-based inference, model quantization, and performance tuning (25%)
Vector Databases & RAG
- Practical experience with open-source vector databases such as Qdrant, Chroma, Milvus, or pgvector (25%)
- Proven implementation of Retrieval-Augmented Generation (RAG) pipelines (25%)
- Experience generating and managing embeddings and metadata filtering (25%)
Security & Governance
- Understanding of data privacy, air-gapped deployments, and enterprise security requirements (25%)
- Experience implementing access controls and audit logging (25%)
Nice to Have
- Experience with LangChain or LlamaIndex
- Exposure to Rust, Go, or C for high-performance services
- Familiarity with Docker and Kubernetes for on-prem deployments
- Knowledge of inference frameworks (e.g., vLLM, llama.cpp, Hugging Face Transformers)
- Prior work in regulated or enterprise environments
Deliverables
- Reference architecture and deployment guidance
- Working prototype (LLM vector DB RAG)
- Documentation and knowledge transfer to internal teams
For immediate consideration please click APPLY.