About the Role

We are looking for an AI Engineer to build and scale production-grade AI capabilities across our core backend services. You will design agentic workflows, integrate LLM-powered endpoints, and work on delivery lifecycle from prototype to production reliability.
Primary Scope
Design, implement, and maintain AI/LLM features across backend services.
Build secure, observable API integrations for AI use cases in consumer-facing journeys.
Partner with product, design, and frontend teams to ship AI features with measurable business impact.
Key responsibilities of the AI Engineer shall include (but not be limited to):
Collaborate with Product and Design teams to identify and build agentic AI use cases for consumer-facing journeys.
Design and implement agentic workflows with planning and execution loops, secure tool/function calling, and robust failure handling.
Build RAG pipelines, including document ingestion, chunking, embeddings, vector indexing, retrieval tuning, and grounded responses with citations where required.
Develop secure and scalable AI APIs,



SDKs, and integrations for frontend, internal systems, data sources, and third-party tools.
Implement authentication, least-privilege access, RBAC, rate limits, retries, timeouts, budget controls, and provider failover strategies.
Apply safety and compliance guardrails such as PII redaction or masking, content moderation, audit logging, and policy-aligned access controls.
Define and automate evaluation frameworks to measure task success, response quality, hallucination, latency, and cost.
Set up observability for AI systems using traces, metrics, logs, dashboards, and cost or latency monitoring.
Optimize reliability, performance, and cost through caching, queuing, retries, timeouts, and model/provider fallback mechanisms.
Contribute to CI/CD, infrastructure-as-code, automated testing, and production deployment processes.
Drive production readiness through explicit documentation, runbo

📌 Ai Engineer Gurugram
🏢 Velocitai Digital
📍 Gurugram