-
Experience with Linux system administration, CLI, and shell scripting
-
Proficiency in containerization: Docker, Podman, containerd
-
Experience deploying containerized services with Kubernetes or Docker Compose
-
Recent software development using Python and Golang
-
Familiarity with RAG pipelines, LLMs, and embedding models
-
Experience with CI/CD using GitLab CI
-
Proficiency in using Prometheus and Grafana for monitoring
-
Experience with Git source control
-
Experience debugging GPU-enabled applications
-
Familiarity with LLM orchestration (e.g., OpenAI API)
-
Experience with distributed processing frameworks like Spark, Dask, or Ray for ETL workflows
-
Proficiency in SQL, Elasticsearch, and vector databases
-
Knowledge of HTMX or Hyper-script
-
Experience with multi-node, multi-GPU AI model training (HW/SW)
-
Knowledge of AI inferencing frameworks: Nvidia NIM/TRITON, vLLM, Ray
-
Familiarity with the Atlassian suite: Confluence, Jira
Company
Location
Maryland - United States of America
Job type
Full-Time
Golang Job Details
Job Title:
Software Engineer RAG / LLM Deployment
Location:
Onsite
Job Type:
Full-Time / Contract
Compensation:
Up to $112/hr
Experience: 7 Years of Experience + Bachelor's Degree
Overview:
The Software Engineer will be responsible for the design, development, and deployment of a Retrieval Augmented Generation (RAG) solution in a High Performance Computing (HPC) Linux environment. This position requires hands-on expertise with Large Language Models (LLMs), RAG pipelines, orchestration frameworks, and security-aware AI systems.
Required Skills:
Desired Skills:
More Developer Job Boards
Fullstack Developer Jobs Golang Jobs JavaScript Jobs Python Jobs React Jobs Rust Jobs Java Jobs