What are the responsibilities and job description for the Senior Engineer position at Noah AI?
The Vision
At Noah, we’re building what comes after apps:
An operating system for executive intelligence - ambient, agentic AI that runs your work life quietly. Noah is part of your work flow - email, calendar, Slack, voice, SMS. Noah comes to you and you don't go to Noah.
Not a chatbot.
Not an assistant.
A fully autonomous operator that can reason, plan, remember, and act across your digital world.
Think
- Tool-using agents with persistent memory
- Long-horizon reasoning
- Real-time context fusion across modalities
- Personalized execution at human-assistant level accuracy
- A cognitive layer that sits above your entire workstack
If we succeed, every knowledge worker will have a 24/7 autonomous executive operator.
Noah becomes the OS for professional productivity.
We’re still early(in stealth), but the mission is massive: to make one billion people radically more productive. Our first agent is ready at www.heynoah.io.
To see how Noah lands with real users, here’s a recent LinkedIn post endorsing Noah.
Founder
Ashish Toshniwal is a serial entrepreneur and product visionary who believes AI can give every professional their own “second self.” He previously founded Y Media Labs (YML), which he bootstrapped into a 600-person digital product agency valued at $350M. You can learn about him here - https://www.ashishtoshniwal.com/
About the Role
We’re looking for a hands-on senior engineer to help build the next generation of agentic AI systems — deeply integrated, multimodal, context-aware agents capable of reasoning, executing tasks, and scaling across real-world workloads. You’ll own core backend systems that connect AI models with users, memory, and data — powering agents that feel both intelligent and human. This role blends backend engineering, AI application design, and systems thinking.
You’ll work closely with product and research teams to bring applied AI ideas into production, focusing on robustness, observability, and performance at scale.
Responsibilities
- Architect and build scalable agentic frameworks: orchestration layers, memory systems, context pipelines, and multimodal inference services.
- Design and maintain real-time infrastructure using sockets, WebSockets, queues, and event streams.
- Implement secure, fault-tolerant APIs that serve as the foundation for AI-driven assistants.
- Integrate AI models and tools (LLMs, vision, audio, embeddings) with robust backend systems.
- Contribute to prompt engineering, evaluation, and context optimization to ensure high-quality model outputs.
- Define and measure eval pipelines (behavioral, functional, and regression testing) to validate agent reliability.
- Collaborate on data storage and retrieval strategies across SQL, NoSQL, and vector databases.
- Optimize cloud infrastructure for cost, latency, and reliability (Google Cloud preferred, but not required).
- Champion best practices for security, authentication, and access control in distributed AI systems.
Qualifications
- 5 years in backend or distributed systems.
Required Skills
- Strong background in backend or distributed systems (Python, Go, or similar).
- Experience with WebSockets / real-time messaging architectures.
- Deep understanding of scaling systems and debugging production performance issues.
- Working knowledge of cloud platforms (GCP, AWS, or Azure).
- Solid grasp of authentication, authorization, and secure API design.
- Familiarity with prompt engineering, evals, and context pipelines for AI applications.
- Comfort with SQL and NoSQL storage systems.
- Understanding of multimodal AI systems (language, vision, audio, or embeddings).
- Strong debugging, observability, and structured logging habits.
Nice-to-have
• Experience with agent frameworks (LangGraph, Semantic Kernel, CrewAI, etc.).
• Background in machine learning or model inference optimization.
• Experience integrating retrieval-augmented generation (RAG) or memory systems.
• Knowledge of structured evaluations for AI systems (model QA, test harnesses).
• Familiarity with GCP services (Pub/Sub, Cloud Run, Cloud SQL, Artifact Registry, etc.)