Senior AI/RAG Software Engineer (Software Engineer Level 3 – SWE3)
Wyetech is seeking an experienced Senior AI/RAG Software Engineer (SWE3) to design, develop, deploy, and support Retrieval-Augmented Generation (RAG) solutions within a high-performance computing (HPC) Linux environment. This position focuses on integrating Large Language Models (LLMs), knowledge retrieval systems, embedding models, and containerized applications to deliver scalable, secure, production-ready AI solutions supporting mission-critical operations.
The ideal candidate will possess strong Python development experience, expertise in Kubernetes and container orchestration, and a solid understanding of Generative AI technologies, CI/CD automation, and DevSecOps practices.
Required Skills/Experience:
Advanced experience working in Linux environments, including command-line development, system administration, and troubleshooting.
Recent hands-on Python software development experience using modern software engineering practices and frameworks.
Experience with containerization technologies, including Docker, Podman, and containerd, for application packaging, deployment, and lifecycle management.
Experience designing, authoring, and deploying Helm charts to manage Kubernetes-based applications and services.
Experience configuring and managing Kubernetes resources, including Deployments, Services, ConfigMaps, Secrets, Ingresses, and Operators.
Experience developing, deploying, troubleshooting, and sustaining containerized applications in production environments.
Working knowledge of Generative AI technologies, including LLMs, RAG architectures, embedding models, knowledge retrieval systems, and vector databases.
Experience implementing and maintaining CI/CD pipelines using GitLab CI/CD, Flux CD, GitLab Runners, or comparable technologies.
Experience with observability, logging, metrics, and monitoring tools, including Prometheus and Grafana.
Proficiency with Git-based source control workflows, branching strategies, code reviews, and collaborative development.
Understanding of software development lifecycle (SDLC) best practices, automated testing, security scanning, code quality analysis, and DevSecOps principles.
Desirable Skills:
Experience developing, deploying, and troubleshooting mission applications within AWS cloud environments.
Familiarity with Atlassian collaboration tools, including Jira and Confluence.
Experience developing, troubleshooting, and optimizing GPU-enabled applications.
Experience with machine learning frameworks such as PyTorch and TensorFlow.
Familiarity with ML pipelines and frameworks such as Kubeflow, NVIDIA NeMo, and PyTorch Lightning.
Experience with SQL, Elasticsearch, and vector databases.
Knowledge of AI inference solutions such as NVIDIA NIM, NVIDIA Triton, vLLM, and Ray.
The Software Engineer designs, develops, tests, deploys, documents, maintains, and enhances complex software systems based on documented requirements. These systems may include processing-intensive analytics, real-time applications, large-scale data repositories, data transport services, and cloud-based technologies.
The engineer applies software development methodologies, configuration management practices, and system integration principles while collaborating with technical teams to deliver reliable, secure, and scalable solutions.
Responsibilities and Capabilities:
Design, develop, deploy, and maintain RAG-based applications integrating LLMs, embedding models, and knowledge retrieval systems.
Develop and optimize Python applications supporting AI-driven analytical capabilities within HPC Linux environments.
Build, configure, and manage containerized applications and Kubernetes infrastructure using Helm and related technologies.
Implement and maintain CI/CD pipelines, automated testing, and secure software deployment processes.
Integrate AI/ML applications with enterprise systems, databases, APIs, and supporting infrastructure.
Monitor and troubleshoot…