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
