Lead Software Engineer - AI Agents

Team: Engineering

Location: Noida, Bangalore

Commitment: Full Time

Workplace Type: hybrid

About Level AI

Level AI is on a mission to turn every customer interaction into a strategic advantage. Our AI-native platform helps enterprises transform contact centers from cost centers into engines of customer intelligence, operational efficiency, and business growth. By combining advanced AI with deep domain understanding of customer experience, Level AI empowers teams to unlock actionable insights, automate workflows, and deliver more consistent, higher-quality support across the customer journey.

Headquartered in Mountain View, California, Level AI is a Series C company backed by leading investors including Battery Ventures and ENIAC. Our platform leverages Large Language Models and Custom Small Language Models (SLMs) to power AI Agents across the entire CX journey—customer-facing agents, agent-assist, and backend automation—along with deep conversation analytics for QA, coaching, and insights.

With a fast-growing team in India, we are building a strong engineering presence in Noida to drive innovation across our platform.

About the role

As a Lead Engineer – AI Agents, you will play a critical role in building the scalable backend systems that power Level AI’s next-generation AI Agents. These systems operate in real-time, high-volume enterprise environments and are central to delivering intelligent, production-grade AI experiences.

This role is based in Noida (Delhi NCR) with a hybrid work model (2–3 days/week in office).

You will work at the intersection of distributed systems, cloud infrastructure, and AI-powered applications—bringing agentic AI capabilities into production at scale.

Responsibilities -

• Design and build scalable backend systems powering AI Agents that operate in real-time enterprise environments

• Develop agent orchestration frameworks (multi-step reasoning, tool usage, decisioning workflows)

• Build systems for agent memory, context management, and state persistence across interactions

• Architect low-latency inference pipelines integrating LLMs, SLMs, and external tools/services

• Implement evaluation (evals) frameworks to measure agent performance, accuracy, and reliability

• Enable continuous improvement loops (feedback → retraining → deployment) for AI agents in production

• 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 robust APIs and service layers (REST / gRPC) for agent capabilities

• Partner closely with Applied AI / ML teams to productionize models and agent behaviors

• Collaborate with Product and Solutions teams to translate real customer workflows into agentic systems

• Drive best practices in observability, monitoring, safety, and guardrails for AI systems

• Contribute to architecture decisions for scaling multi-tenant, enterprise-grade AI platforms

Requirement -

• 5+ years of experience in backend engineering, distributed systems, or platform engineering

• Strong experience building high-scale, production-grade backend systems

• Experience designing systems for real-time processing, streaming, or event-driven architectures

• Strong understanding of API design (REST, gRPC) and microservices architectures

• Experience with databases (SQL + NoSQL) and data modeling for high-scale systems

• Hands-on experience with Docker, Kubernetes, and cloud platforms (AWS/GCP/Azure)

• Strong fundamentals in system design, concurrency, and performance optimization

Strong Plus (Agent / AI focus):

• Experience working with LLMs, conversational AI, or AI-powered products in production

• Familiarity with agent frameworks, tool calling, or multi-step reasoning systems

• Experience building or integrating RAG pipelines, vector databases, or retrieval systems

• Exposure to evaluation systems (offline/online evals, A/B testing for AI systems)

• Understanding of prompting strategies, context windows, and model behavior optimization

Experience with real-time decisioning systems or workflow orchestration engines