Senior Software Engineer at NVIDIA developing multimodal, production-grade RAG solutions using AI technology. Leading architecture design and implementation of next-gen RAG workflows with a focus on GPU performance.
Responsibilities
Plan, build and refine a GPU-accelerated, scalable, configurable Retrieval Augmented Generation (RAG) workflow and optimize it for accuracy, relevance, grounding and performance.
Design and implement AI agents to enhance RAG pipeline which are capable of reasoning, planning, multi-step execution, and collaboration across tools and services
Run fast, high-quality POCs on emerging agent and RAG architectures; harden successful patterns into generalized, reusable implementations and integrate them as part of production software.
Build and deploy a disaggregated, end-to-end RAG pipeline using on-prem microservices architecture, orchestrating complex, multi-service deployments from local Docker environments to enterprise-scale Kubernetes clusters.
Drive the continuous improvement of the pipelines by rigorously evaluating system accuracy, characterizing performance metrics across components, analyzing the data and recommending actionable strategic enhancements.
Collaborate with various teams on new product features and the improvement of existing product.
Provide guidance and support to NVIDIA internal teams and external partners on domain-adaptation, customization and integration of the RAG pipeline.
Champion engineering excellence by leading rigorous code, architecture, and test plan reviews, authoring robust user documentation, and driving collaborative problem-solving and triage initiatives.
Drive software excellence by designing with clean architectural patterns and automating the path to production through advanced CI/CD, testing, and telemetry workflows.
Requirements
5+ years of professional software engineering experience, with deep expertise in Python, and AI applications.
Bachelor's degree or Master’s degree (or equivalent experience) in Computer Science, Electrical Engineering, Data Science, Artificial Intelligence or other related fields
Hands-on experience building and deploying LLM-powered AI applications or RAG or Agentic AI workflows.
Strong understanding of LLM design patterns, including tool calling, prompt engineering, structured outputs, reasoning.
Experience with agent frameworks or orchestration systems such as LangGraph, LangChain, OpenAI Agents SDK, or similar.
Have working experience with microservices, Docker, Helm, Kubernetes.
Experience with end-to-end software lifecycle, release packaging, and CI/CD pipelines.
Strong collaborative and interpersonal skills, specifically a proven ability to effectively guide and influence within a dynamic environment involving teams across the globe.
Tech Lead leading technical team in developing innovative applications for Porto Bank's digital services. Focusing on high scalability and cloud - native solutions within AWS environment.
Senior Software Engineer designing scalable backend services for financial solutions at DailyPay. Leading architectural evolution and mentoring engineers while ensuring high - quality backend operations.
Software Engineer Intern at FireMon designing and building user - friendly firewall management solutions. Collaborating across agile teams to enhance security operations and customer value.
RevOps Engineer creating operational systems for NHS growth team. Managing CRM and data infrastructure for efficient lead generation and sales processes with a high degree of ownership.
Senior Integrations Engineer designing and building healthcare data integrations for a tech startup. Working closely with health system customers to enhance integration capabilities while ensuring quality and security.
Software Engineer developing backend services for Trustpilot's fraud detection systems. Building scalable enforcement pipelines and maintaining internal tools in a hybrid work environment.
Software Engineer I at Trustpilot working on backend services for fraud detection systems. Integrating detection models and maintaining internal tools within a hybrid team.
Software Engineer building backend services for Trustpilot's fraud detection systems. Responsible for integrating models and maintaining internal tools while collaborating with a new team.
Linux & Kubernetes Administrator managing on - premise AI hardware and Linux server infrastructures at Fronius. Supporting Data Scientists and Engineers in maintaining Kubernetes and Docker environments.
Alternant Ingénieur en informatique au sein de Thales, participant à des projets inédits en services numériques. Formation pratique et académique dédiée à l'IT et à l’ingénierie.