Job Description :
Trigyn has a long-term contract opportunity for Software Developer / Engineer with our direct client - a major utility services firm based in Philadelphia, Pennsylvania (Hybrid). Details on the role are listed below :
NOTE :
- Hybrid work. 3 days onsite (Philadelphia, PA).
- Only local candidates preferred.
- In-person interview is required.
Consultant Requirements – On-Prem LLM & Vector DB Implementation
Core Experience :
Hands-on experience deploying open-source LLMs such as Meta Llama 3 and Mistral / Mixtral in on-prem or private environmentsStrong proficiency in Python for LLM inference, prompt engineering, and integrationExperience with CPU-based inference, model quantization, and performance tuningVector Databases & RAG
Practical experience with open-source vector databases such as Qdrant, Chroma, Milvus, or PgvectorProven implementation of Retrieval-Augmented Generation (RAG) pipelinesExperience generating and managing embeddings and metadata filteringSecurity & Governance
Understanding of data privacy, air-gapped deployments, and enterprise security requirementsExperience implementing access controls and audit loggingNice to Have :
Experience with LangChain or LlamaIndexExposure to Rust, Go, or C++ for high-performance servicesFamiliarity with Docker and Kubernetes for on-prem deploymentsKnowledge of inference frameworks (., vLLM, , Hugging Face Transformers)Prior work in regulated or enterprise environmentsDeliverables :
Reference architecture and deployment guidanceWorking prototype (LLM + vector DB + RAG)Documentation and knowledge transfer to internal teams.