The company is looking to solve mission-critical knowledge retrieval and orchestration tasks by developing secure, LLM-based AI systems, specifically a Retrieval Augmented Generation (RAG) solution in a high-performance computing (HPC) Linux environment.
Requirements
- Python
- Golang
- Linux CLI
- shell scripting
- Docker
- PodMan
- containerd
- Kubernetes
- Docker Compose
- GitLab CI
- Git
- Prometheus
- Grafana
- GPU-enabled application debugging
- LLM orchestration tools
- OpenAPI
- Spark
- Dask
- Ray
- SQL
- Elasticsearch
- Vector databases
- HTMX
- HyperScript
- Nvidia NIM
- Triton
- vLLM
- Atlassian tools
- Confluence
- Jira
Responsibilities
- Develop and deploy containerized services using Docker, PodMan, containerd, and Kubernetes/Docker Compose orchestration.
- Write and maintain clean, scalable code using Python and Golang.
- Support the design and optimization of RAG pipelines, large language models (LLMs), and embedding systems.
- Configure and manage CI/CD pipelines using GitLab CI and source control using Git.
- Administer and monitor systems using tools such as Prometheus and Grafana.
- Contribute to system performance, reliability, and security by applying expert-level Linux CLI and shell scripting knowledge.
Other
- TS/SCI with Poly
- 2 - 14+ years of relevant software engineering experience
- Bachelor’s degree in Computer Science, Engineering, or related field
- Flexible Schedules and Remote Work Options
