Be an Early Applicant
The Role
The role involves deploying open-source LLMs and vector databases, implementing RAG pipelines, and ensuring security and governance in on-prem environments.
Summary Generated by Built In
Title: Software Developer/Engineer (Mid Level experience)
Duration: 12 Months
Location: Philadelphia, PA
Note: Hybrid role, minimum 3 days in the office
Interview: 1st interview, 1-hour, in-person; 2nd interview, 1-hour, in-person
Job description:
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 environments
- Strong proficiency in Python for LLM inference, prompt engineering, and integration
- Experience with CPU-based inference, model quantization, and performance tuning
Vector Databases & RAG
- Practical experience with open-source vector databases such as Qdrant, Chroma, Milvus, or pgvector
- Proven implementation of Retrieval-Augmented Generation (RAG) pipelines
- Experience generating and managing embeddings and metadata filtering
Security & Governance
- Understanding of data privacy, air-gapped deployments, and enterprise security requirements
- Experience implementing access controls and audit logging
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
"If you are: bright, motivated, skilled, a difference-maker, able to get things done, work with minimum direction, enthusiastic, a thinker, able to juggle and multi-task, communicate effectively, and lead, then we would like to hear from you. We need exceptionally capable people for this role for our client, so get back to us and tell us why you think you are a fit."
About Us:
Since 2000, Tri-Force Consulting Services (https://triforce-inc.com) has been an MBE/SDB certified IT Consulting firm in the Philadelphia region. Tri-Force specializes in IT staffing, software development (web and mobile apps), systems integration, data analytics, system automation, cybersecurity, and cloud technology solutions for government and commercial clients. Tri-Force works with clients to overcome obstacles such as increasing productivity, increasing efficiencies through automation, and lowering costs. Our clients benefit from our three distinguishing core values: integrity, diligence, and technological excellence. Tri-Force is a six-time winner among the fastest-growing companies in Philadelphia and a four-time winner on the Inc. 5000 list of the nation's fastest-growing companies.
Skills Required
- Hands-on experience deploying open-source LLMs
- Proficiency in Python for LLM inference and integration
- Experience with vector databases and generating embeddings
- Understanding of data privacy and enterprise security
- Experience with Docker and Kubernetes
Am I A Good Fit?
Get Personalized Job Insights.
Our AI-powered fit analysis compares your resume with a job listing so you know if your skills & experience align.
Success! Refresh the page to see how your skills align with this role.
The Company
What We Do
Tri-Force Consulting Services, Inc. is a U.S.-based IT consulting and staffing agency that provides comprehensive IT solutions, including AI-powered services, custom software development, cybersecurity, cloud technology, and IT staffing to government and commercial sectors.
