Job DescriptionAI Engineer — Agentic AI, RAG & Low-Latency Voice Systems
nMobiloitte Technologies (I) Pvt. Ltd. | New Delhi (in office / hybrid) | Full-time | 5+ years
nCompensation: No ceiling for the right candidate.
nTwo things decide this role: how well you handle latency, and how far past basic RAG you can build.
nMobiloitte builds production AI for enterprise clients across India, the US, UK, UAE, Singapore and South Africa. We're hiring a senior AI Engineer to own our agentic AI, retrieval and voice stack — systems that go live, carry real call volume, and stay up.
n1. LATENCY IS THE JOB, NOT A DETAIL
nOur voice bots handle inbound and outbound calls where a 400ms difference decides whether the conversation feels human. We need someone who treats latency as an engineering discipline:
n
- n
- Owns end-to-end voice latency from user speech to first token of bot audio — and can quote the numbers they achievedn
- Profiles and attacks each hop: STT, retrieval, inference, TTS, networkn
- Streaming responses, speculative/partial generation,



response chunking to shorten time-to-first-audion
- Barge-in and interruption handling that actually works mid-sentencen
- Model caching, warm pools, batching, concurrency control under real call loadn
- Knows when the fix is architectural, not a bigger GPUn

nIf you can't tell us what your p95 latency was and what you did to bring it down, this isn't the role.
n2. AGENTIC AI — BEYOND BASIC RAG
nSingle-shot retrieve-and-answer is table stakes. We're building systems that plan, act and self-correct:
n
- n
- Agent orchestration — LangGraph, CrewAI, AutoGen, OpenAI Agents SDK, or your own framework (we care that you've built it, not which one)n
- Tool and function calling, API/DB actions, structured outputsn
- Multi-step reasoning, task decomposition, planning loops with retry and fallbackn
- Multi-agent patterns — routing, supervisor/worker, handoffsn
- Conversation and long-term memory management across sessio

📌 AI Engineer (Okhla)
🏢 Mobiloitte
📍 Okhla