2 years ago
Bengaluru, IndiaStaff+
Responsibilities
- Design and build scalable backend systems powering real-time AI Agents in enterprise environments.
- Develop agent orchestration frameworks for multi-step reasoning, tool usage, and decisioning workflows.
- Build agent memory, context management, and state persistence systems.
- Architect low-latency inference pipelines integrating LLMs, SLMs, and external tools and services.
- Implement evaluation frameworks and continuous improvement loops for AI agents.
- Design and manage event-driven, asynchronous workflows for complex agent tasks.
- Optimize systems for high throughput, low latency, and cost-efficient inference at scale.
- Build and maintain REST and gRPC APIs and service layers for agent capabilities.
- Partner with Applied AI and ML teams to productionize models and agent behaviors.
- Collaborate with Product and Solutions teams to translate customer workflows into agentic systems.
- Drive observability, monitoring, safety, and guardrails for AI systems.
- Contribute to architecture decisions for scalable, multi-tenant, enterprise-grade AI platforms.
Requirements
- 5+ years of experience in backend engineering, distributed systems, or platform engineering.
- Strong experience building high-scale, production-grade backend systems.
- Experience designing real-time processing, streaming, or event-driven architectures.
- Strong understanding of REST and gRPC API design and microservices architectures.
- Experience with SQL and NoSQL databases and high-scale data modeling.
- Hands-on experience with Docker, Kubernetes, and AWS, GCP, or Azure.
- Strong fundamentals in system design, concurrency, and performance optimization.
- Strongly preferred: experience with LLMs, conversational AI, or AI-powered products in production.
- Strongly preferred: familiarity with agent frameworks, tool calling, or multi-step reasoning systems.
- Strongly preferred: experience building or integrating RAG pipelines, vector databases, or retrieval systems.
- Strongly preferred: exposure to offline or online evaluation systems and A/B testing for AI systems.
- Strongly preferred: understanding of prompting strategies, context windows, and model behavior optimization.
- Strongly preferred: experience with real-time decisioning systems or workflow orchestration engines.
Benefits
- Competitive compensation with performance-based upside.
- Flexible vacation policy.
- Health insurance coverage.
- Globally distributed, high-impact team.
- Opportunity to build cutting-edge AI products at scale.
- Regular team offsites and in-person collaboration.
- Hybrid work model in Noida with 2–3 days per week in the office.
Tech Stack
Categories
About Level AI
Level AI builds a conversational intelligence platform for enterprise contact centers, combining speech AI, NLP, and retrieval to analyze customer interactions and drive QA, coaching, automation, and analytics. It sells its software to large customer service and sales teams, typically via subscription. Founded in 2018 and headquartered in Mountain View, the company is Series C–funded, with customers such as Wayfair, Smartsheet, Chime, Gusto, and Swiss Re.