Description

You will design, build, and maintain a high-performance, multithreaded native C++ backend runtime for heavy data workloads.

This role is on-site.

Responsibilities

• Develop and maintain core engine modules including indexing, networking, streaming I/O, and thread management.
• Lead memory reduction initiatives by redesigning internal data structures to increase data density and reduce footprint.
• Profile and debug the runtime in memory-constrained Docker environments to prevent OOM failures and ensure stability.
• Ensure the C++ core interfaces seamlessly with high-level SDKs like Python and TypeScript.
• Optimize execution paths using low-level hardware techniques such as SIMD bit-packing (AVX2/NEON).

Required Skills

• Advanced C++ with deep expertise in multithreading, memory management, and modern standards.
• Experience building complex system libraries using CMake.
• Strong background in optimizing data structures, including compressing inverted indexes.
• Proficiency in benchmarking and profiling systems within containerized environments.
• Minimum 5+ years of experience in systems programming.
• Understanding of search index architectures and posting list compression.

Preferred Skills

• Familiarity with advanced compression techniques like delta encoding, Elias-Fano, and Roaring Bitmaps.
• Experience with LLM APIs, vector databases, and RAG workflows.

Key Skills

Education

Any Gradute