Senior Backend Engineer - Singapore

About Plaud Inc.

Plaud is building the real-world AI interface for professionals to amplify intelligence, elevate productivity and performance, loved by over 2,000,000 users worldwide since 2023. With a mission to amplify human intelligence, Plaud captures, structures, and compounds the intelligence generated in conversations — so humans can think better, decide faster, and execute with clarity.

Plaud Inc. is a Delaware-incorporated, San Francisco-based company pushing the boundary of human–AI intelligence through a hardware–software combination. With full ISO 27001, ISO 27701, SOC 2, GDPR, EN18031, and HIPAA compliances, Plaud is committed to the highest standards of data security and privacy protection.

Why You Should Join Us

Plaud is building the next generation intelligence infrastructure and interfaces to capture, extract, and utilize intelligence from what people say, hear, see, and think.

• Plaud is a bootstrapped, skyrocketing, profitable company with a $250M revenue run rate achieved in just three years.
• Define the next-gen paradigm for human-AI interaction.
• Gain exposure to cutting-edge AI for Pro tools and play a direct role in our global expansion.
• Work with passionate teammates who value innovation, collaboration, and customer success.
• Grow your career in a culture that champions continuous learning and fast career development.
• Market-competitive compensation, global exposure, and a vibrant, creativity-fueled work atmosphere.

What You Will Do

1. Build production-grade ContextOS infrastructure for Agent Context Engineering — context construction, compression, scheduling, injection, and long/short-term memory management — powering Agent task planning and autonomous execution.

2. Own the end-to-end retrieval pipeline: offline document parsing, semantic chunking, embedding, and index construction, plus online query understanding & rewriting, hybrid recall (sparse + dense), and multi-stage reranking — delivering high-quality, low-latency context for real-time Agent decisions

3. Implement Agentic RAG driven by LLM reasoning — a Loop Agent executing iterative Thought → Action → Observation cycles, evolving knowledge acquisition from single-pass recall to autonomous deep exploration.

4. Continuously integrate frontier LLM, Embedding, and Reranker models, and optimize end-to-end retrieval performance — p99 latency, throughput, and service robustness — keeping online retrieval fast and reliable.

5. Work closely with product and engineering teams to ship Agent capabilities into core product experiences users can feel.

Why You Should Join Us

1. Be part of building Agent + Search/Retrieval + RAG、MAG from the ground up — every line of code you write shapes the experience of millions of real users.

2. A highly skilled and specialized team, with outcome-driven engineering, fast iteration cycles, and a sharp focus on problems that truly matter.

3. Deep exposure to cutting-edge Agentic system design paradigms, evolving retrieval architectures, and multimodal AI applications — with direct ownership of end-to-end Agent context system engineering

4. The systems you build will redefine how people interact with intelligent services.

Skills, Qualifications and Experience We Look for

1. Min. 5 years of engineering experience in Search, Recommendation, RAG, or AI Agent systems; strong programming fundamentals with proficiency in Golang or equivalent.

2. Deep expertise across the full retrieval stack — inverted-index and vector search engines, hybrid recall + multi-stage ranking, and Embedding/Reranker model selection, pipeline integration, and tuning — with proven end-to-end architecture design experience.

3. Solid RAG engineering depth: chunking strategies, query understanding/rewriting, context assembly, and retrieval quality evaluation; understands common failure modes (e.g., hallucination, context overflow) and their mitigations.

4. Proven track record shipping AI Agent applications in production — reasoning, tool use, and context/memory management — with experience running large-scale online systems against strict latency and quality SLOs.

5. Strong cross-functional collaborator, able to partner with product and engineering to deliver end-to-end AI features.