Role Overview: GenAI Engineer We are seeking a GenAI Engineer with 3–6 years of experience to design and build production-grade AI systems using Large Language Models (LLMs), Retrieval-Augmented Generation (RAG), and agent-based architectures. This role requires strong engineering depth combined with applied AI expertise to deliver scalable, reliable, and efficient AI-powered applications. 
 What You'll Do & The Impact You'll Have
-Design and build production-grade AI features leveraging LLMs, RAG pipelines, and agent-based systems. 
-Implement end-to-end RAG pipelines including retrieval strategies, embeddings, vector search optimization, context orchestration, guardrails, and fallback mechanisms. 
-Orchestrate agent workflows using frameworks such as LangGraph, LangChain, or similar, ensuring clear state management and safe multi-step reasoning.
-Develop and deploy cloud-native microservices and APIs (REST/gRPC) to serve AI applications at scale. 
-Build and optimize event-driven architectures for real-time AI system interactions. 
-Work with graph databases (e.g., Neo4j, Amazon Neptune) to model and query complex relationships. 
-Fine-tune models and optimize performance for domain-specific use cases. 
-Ensure production reliability including latency optimization, throughput scaling, token efficiency, and cost control. 
-Implement observability, monitoring, and logging for AI systems, including prompt/model versioning and rollback strategies. 
-Collaborate with cross-functional teams including data scientists, engineers, and product stakeholders to deliver impactful AI solutions


 

Must-Have Skills:
-Experience: 3–6 years in AI/ML engineering, software engineering, or applied AI roles. 
-Hands-on experience building production-grade applications using LLMs, RAG, and agent-based systems. 
-Strong programming skills in Python, with exposure to Node.js, Java, or Go. 
-Experience designing cloud-native architectures including microservices, REST/gRPC APIs, and event-driven systems. 
-Solid understanding of embeddings, vector databases, and retrieval strategies.
-Experience with agent orchestration frameworks (e.g., LangChain, LangGraph) or similar. 
-Exposure to model fine-tuning and performance optimization techniques. 
-Experience working with graph databases such as Neo4j or Amazon Neptune. 
-Strong understanding of system performance, scalability, and cost optimization in AI systems. 
-Experience implementing observability, monitoring, and debugging for production systems. 
-Strong problem-solving skills and ability to work in a fast-paced, collaborative environment.

Nice-to-Have Skills:
-Experience with cloud platforms (AWS, GCP, or Azure) for deploying AI systems. 
-Familiarity with containerization and orchestration (Docker, Kubernetes). 
-Exposure to prompt engineering techniques and evaluation frameworks. 
-Experience working in consulting or client-facing environments.