AI Engineer — Agentic AI, RAG & Low-Latency Voice Systems
Mobiloitte Technologies (I) Pvt. Ltd. | Recent Delhi (in office / hybrid) | Full time | 5+ years
Compensation: No ceiling for the right candidate.

Two things decide this role: how well you handle latency, and how far past basic RAG you can build.

Mobiloitte 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.
LATENCY IS THE JOB, NOT A DETAIL

Our 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:
Owns end-to-end voice latency from user speech to first token of bot audio — and can quote the numbers they achieved
Profiles and attacks each hop: STT, retrieval, inference, TTS, network
Streaming responses, speculative/partial generation, response chunking to shorten time-to-first-audio




Barge-in and interruption handling that actually works mid-sentence
Model caching, warm pools, batching, concurrency control under real call load
Knows when the fix is architectural, not a bigger GPU

If you can‘t tell us what your p95 latency was and what you did to bring it down, this isn‘t the role.
AGENTIC AI — BEYOND BASIC RAG

Single-shot retrieve-and-answer is table stakes. We‘re building systems that plan, act and self-correct:
Agent orchestration — LangGraph, CrewAI, AutoGen, OpenAI Agents SDK, or your own framework (we care that you‘ve built it, not which one)
Tool and function calling, API/DB actions, structured outputs
Multi-step reasoning, task decomposition, planning loops with retry and fallback
Multi-agent patterns — routing, supervisor/worker, handoffs
Conversation and long-term memory management across sessions
Advanced retrieval: agentic and query-rewriting RAG, hybri

📌 Ai Engineer — Agentic Ai, Rag Okhla
🏢 Mobiloitte
📍 Okhla