As an Engineering Lead at Lyzr, you will own the execution, quality, and scalability of the GenAI platform and customer-facing agentic systems.
This is a hands-on leadership role at the intersection of backend engineering, distributed systems, and GenAI infrastructure. You will lead engineers building core platform primitives such as agent orchestration, RAG pipelines, LLM integrations, and observability systems.
You will work closely with Solutions Architects, Product Managers, and Customers to ensure GenAI architectures are translated into systems that ship, scale, and remain stable in production.
Lead engineers building Lyzr’s GenAI platform and agent infrastructure using Python and FastAPI, with a strong focus on correctness, performance, and maintainability.
Own end-to-end delivery of platform and customer-facing capabilities, from technical design and implementation through testing, deployment, and production operations.
Translate high-level GenAI and agentic architectures into scalable backend systems, making pragmatic trade-offs between flexibility, reliability, and time-to-market.
Review, influence, and take ownership of system architecture, data models, API contracts, and critical code paths across services.
Design, build, and scale multi-agent orchestration systems, including tool execution, memory management, state handling, and long-running workflows.
Implement and evolve production-grade Retrieval-Augmented Generation (RAG) pipelines, covering ingestion, chunking, indexing, retrieval, re-ranking, and context assembly.
Design and maintain APIs for agents, tools, microservices, and external system integrations, ensuring clear contracts and backward compatibility.
Optimize LLM usage across the platform for latency, throughput, cost efficiency, and reliability, including model selection, request shaping, and caching strategies.
Build strong observability into GenAI systems, including structured logging, metrics, tracing, and alerting to diagnose failures and performance issues.
Own incident response for production systems, drive root cause analysis, and implement long-term reliability and resilience improvements.
Partner closely with Solutions Architects to validate technical feasibility, execution plans, and delivery risks for customer and platform initiatives.
Collaborate with Product Managers to shape the roadmap, balancing product ambition with engineering rigor and sustainable delivery.
Mentor engineers through design reviews, code reviews, and day-to-day guidance, raising the overall engineering bar across the team.
Implement secure data handling, access controls, and compliance mechanisms to support enterprise AI use cases, including PII-sensitive workflows.
