Senior System Software Engineer, Agentic Retrieval
Core
Develop pipelines for indexing and querying multi-modal content, building powerful, flexible, multi-modal retrievers and agents driven by Large Language Models (LLM) to improve customer experience.
Role type
Senior System Software Engineer (Agentic Retrieval)
Builds
Containerized pipelines for high quality multi-modal datasets, GPU-accelerated data preparation pipelines, and production-level tools for the LLM ecosystem.
Domain
Generative AI, LLM, VLLM, Agentic Retrieval, Multi-modal AI
Deliverable
production ML models
Required skills
Rust, Python, GPU programming, LLM/VLM/Generative AI workflows, MLOps, Docker, Kubernetes, Cloud infrastructure, System optimization, Prompt engineering, Fine-tuning
Preferred skills
Micro-optimization, Benchmarking, Profiling, Continuous Delivery pipeline management, Cross-functional collaboration
Technologies
Rust, Python, Docker, Kubernetes, GPU-accelerated environments
Responsibilities
Develop and optimize Rust-based data processing frameworks for large datasets on GPU; Lead development and optimization of Agentic Retrieval pipeline components; Collaborate with LLM/ML researchers on full-stack data preparation pipelines; Implement benchmarking, profiling, and optimization of algorithms for LLM applications; Build integrated systems for unified user experience; Maintain Continuous Delivery pipelines; Provide peer reviews on performance and scalability.
Seniority
Senior, hands-on IC