Software Developer/Engineer (LLM / Meta Llama 3 / Mistral / Mixtral / Python)
Not Disclosed•ContractorHybrid
location_onRace Street Meetinghouse, 1501, Cherry Street, Logan Square, Center City, Philadelphia, Philadelphia County, Pennsylvania, 19103, United States
About the Role
Trigyn is seeking a Software Developer/Engineer for a long-term contract opportunity with a direct client, a major utility services firm based in Philadelphia, PA. This hybrid role focuses on the implementation of on-premises Large Language Models (LLMs) and Vector Databases to support enterprise-grade AI initiatives.
In this position, you will be responsible for deploying open-source LLMs, such as Meta Llama 3 and Mistral/Mixtral, within secure, private environments. The role involves building Retrieval-Augmented Generation (RAG) pipelines, managing embeddings, and ensuring high-performance CPU-based inference through model quantization and tuning. You will deliver a reference architecture, a working prototype, and comprehensive documentation to facilitate knowledge transfer to the client's internal teams.
About Trigyn
Trigyn is an IT Services Company with over 30 years of experience, currently deploying more than 1,500 resources. We are ISO 9001:2015, ISO 27001:2013 (ISMS), and CMMI Level 5 Certified, and we operate as an E-Verify® Employer.
Equal Opportunity
Trigyn is an Equal Opportunity Employer.
Work location
Work model: Hybrid
Race Street Meetinghouse, 1501, Cherry Street, Logan Square, Center City, Philadelphia, Philadelphia County, Pennsylvania, 19103, United States
Philadelphia, Pennsylvania
Key Responsibilities
- check_circleDeploy open-source LLMs such as Meta Llama 3 and Mistral in on-prem environments
- check_circleImplement Retrieval-Augmented Generation (RAG) pipelines using vector databases
- check_circleDevelop Python code for LLM inference, prompt engineering, and integration
- check_circleOptimize model performance through CPU-based inference and quantization
- check_circleCreate reference architecture and deployment guidance for AI solutions
- check_circleProduce documentation and conduct knowledge transfer to internal teams
Requirements
- verifiedHands-on experience deploying open-source LLMs (Meta Llama 3, Mistral/Mixtral) in on-prem environments
- verifiedStrong proficiency in Python for LLM inference, prompt engineering, and integration
- verifiedExperience with CPU-based inference, model quantization, and performance tuning
- verifiedPractical experience with open-source vector databases (Qdrant, Chroma, Milvus, Pgvector)
- verifiedProven implementation of Retrieval-Augmented Generation (RAG) pipelines
- verifiedExperience generating and managing embeddings and metadata filtering
- verifiedUnderstanding of data privacy, air-gapped deployments, and enterprise security requirements
- verifiedExperience 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.
Similar Job Opportunities
Data Scientist
Software Engineering Institute | Carnegie Mellon University • Pittsburgh, Pennsylvania
Not Disclosedarrow_forward
Python Developer (AWS)
Riva Scientific • East Whiteland Township, Pennsylvania
Not Disclosedarrow_forward
Python Developer
Connecticut Restaurant & Hospitality Association • East Hartford, Connecticut
Not Disclosedarrow_forward
Frequently asked questions about Software Developer/Engineer (LLM / Meta Llama 3 / Mistral / Mixtral / Python) at Trigyn Technologies
What does a Software Developer/Engineer (LLM / Meta Llama 3 / Mistral / Mixtral / Python) at Trigyn Technologies do?expand_more
A Software Developer/Engineer (LLM / Meta Llama 3 / Mistral / Mixtral / Python) at Trigyn Technologies is responsible for the following: Deploy open-source LLMs such as Meta Llama 3 and Mistral in on-prem environments; Implement Retrieval-Augmented Generation (RAG) pipelines using vector databases; Develop Python code for LLM inference, prompt engineering, and integration; and Optimize model performance through CPU-based inference and quantization.
What are the requirements for this Software Developer/Engineer (LLM / Meta Llama 3 / Mistral / Mixtral / Python) role?expand_more
Trigyn Technologies is looking for candidates who meet the following requirements: Hands-on experience deploying open-source LLMs (Meta Llama 3, Mistral/Mixtral) in on-prem environments; Strong proficiency in Python for LLM inference, prompt engineering, and integration; Experience with CPU-based inference, model quantization, and performance tuning; Practical experience with open-source vector databases (Qdrant, Chroma, Milvus, Pgvector); Proven implementation of Retrieval-Augmented Generation (RAG) pipelines; and Experience generating and managing embeddings and metadata filtering.
Where is the Software Developer/Engineer (LLM / Meta Llama 3 / Mistral / Mixtral / Python) role at Trigyn Technologies located?expand_more
Software Developer/Engineer (LLM / Meta Llama 3 / Mistral / Mixtral / Python) at Trigyn Technologies is based in Race Street Meetinghouse, 1501, Cherry Street, Logan Square, Center City, Philadelphia, Philadelphia County, Pennsylvania, 19103, United States. This is a hybrid role.
Is this Software Developer/Engineer (LLM / Meta Llama 3 / Mistral / Mixtral / Python) job remote, hybrid, or on-site?expand_more
Trigyn Technologies has listed this Software Developer/Engineer (LLM / Meta Llama 3 / Mistral / Mixtral / Python) role as hybrid.
How much experience is required for this Software Developer/Engineer (LLM / Meta Llama 3 / Mistral / Mixtral / Python) role?expand_more
Candidates for Software Developer/Engineer (LLM / Meta Llama 3 / Mistral / Mixtral / Python) at Trigyn Technologies should have mid level.
What skills do you need for the Software Developer/Engineer (LLM / Meta Llama 3 / Mistral / Mixtral / Python) role at Trigyn Technologies?expand_more
Key skills for Software Developer/Engineer (LLM / Meta Llama 3 / Mistral / Mixtral / Python) at Trigyn Technologies include Python; Llama 3; Mistral; Mixtral; Cpu-Based Inference; Model Quantization; Performance Tuning; and Qdrant.
What category does the Software Developer/Engineer (LLM / Meta Llama 3 / Mistral / Mixtral / Python) role belong to?expand_more
Software Developer/Engineer (LLM / Meta Llama 3 / Mistral / Mixtral / Python) at Trigyn Technologies is part of the it job category on Recrutus.
About Trigyn Technologies
Trigyn Technologies is an IT services and IT consulting firm headquartered in Mumbai, India, dedicated to re-engineering business operations through transformational digital strategies. The organization assists clients in fundamentally altering their operational models by leveraging technology to address current challenges and prepare for future demands. Its core capabilities bridge the gap between high-level strategy and practical execution across cloud computing, artificial intelligence, data engineering, cybersecurity, enterprise platforms, and large-scale modernization initiatives.
Adopting an AI-forward and accelerator-driven methodology, the company embeds automation and analytics directly into solutions. This approach utilizes proprietary frameworks to reduce risk, accelerate delivery timelines, and improve time to value for complex digital programs. With over three decades of delivery excellence, Trigyn supports mission-critical programs that impact millions of users globally, serving a diverse client base across the Americas, Europe, Asia, and Africa.
Operational integrity is maintained through rigorous adherence to quality and security standards. The firm holds certifications including ISO 9001, ISO 27001, ISO 20000, CMMI Dev V2.0 Level 5, SOC 2, and ISO 14001:2015 for environmental management. Trigyn Technologies Ltd. operates as a publicly traded entity, with Trigyn Technologies, Inc. functioning as its wholly owned US subsidiary, ensuring disciplined execution and secure digital environments for all engagements.
Browse more roles: All Trigyn Technologies jobs, it jobs on Recrutus.