AI Engineer - Voice AI / Autonomous Agents
Who are we?
We are Spyne, redefining how cars are marketed and sold with cutting-edge
Generative AI
. What started as a bold idea using AI-powered visuals to help dealers sell online faster has evolved into a full-fledged AI-first automotive retail ecosystem
. Backed by
$16M in Series A funding
from Vertex Ventures, Accel
, and other top investors, we re scaling fast: Expanded across the
US & EU markets
Launched
industry-first AI-powered Image & 360 solutions
Achieved a
5X revenue surge in 15 months
, aiming for 3-4X growth this year
Now, we re rolling out an
end-to-end GenAI Automotive Retail Suite
and pushing into the US market
to bring our AI-driven products to 3,000-4,000 dealers
.
Read more about us:
Studio AI Product
- t.ly/t0Ko5
Retail AI Product -
t.ly/EyKC9
Series A Announcement -
Spyne raises $16 Mil!
Spyne raising another round!!
Spyne secures funding for US Expansion!
What are we looking for?
We are looking for a
Senior AI Engineer - Voice AI / Autonomous Agents
to own and build Spyne s in-house voice bot stack. This is a high-impact individual contributor role at the intersection of LLMs, ASR/TTS, and voice UX
, focused on creating deeply human, latency-optimized conversations between auto dealerships and their customers. Location: Gurugram (Work from Office, 5 days a week)
What will you do?
Voice AI Stack Ownership:
Build and own the end-to-end voice bot pipeline ASR, NLU, dialog state management, tool calling, and TTS to create a natural, human-like conversation experience.
LLM Orchestration & Tooling:
Architect systems using MCP (Model Context Protocol)
to mediate structured context between real-time ASR, memory, APIs, and the LLM.
RAG Integration:
Implement retrieval-augmented generation
to ground responses using dealership knowledge bases, inventory data, recall lookups, and FAQs.
Vector Store & Memory:
Design scalable vector-based search
for dynamic FAQ handling, call recall, and user-specific memory embedding.
Latency Optimization:
Engineer low-latency, streaming ASR + TTS pipelines and fine-tune turn-taking models for natural conversation.
Model Tuning & Hallucination Control:
Use fine-tuning, LoRA
, or instruction tuning to customize tone, reduce hallucinations, and align responses to business goals.
Instrumentation & QA Looping:
Build robust observability, run real-time call QA pipelines, and analyze interruptions, hallucinations, and fallbacks.
Cross-functional Collaboration:
Work closely with product, infra, and leadership to scale this bot to thousands of US dealerships. What will make you successful in this role?
Architect-level thinking:
You understand how ASR, LLMs, memory, and tools fit together and can design modular, observable, and resilient systems.
LLM Tooling Mastery:
You ve implemented tool calling, retrieval pipelines, function calls
, or prompt chaining across multiple workflows.
Fluency in Vector Search & RAG:
You know how to chunk, embed, index, and retrieve and how to avoid prompt bloat and token overflow.
Latency-First Mindset:
You debug token delays, know the cost of each API hop, and can optimize round-trip time to keep calls human-like.
Grounding > Hallucination:
You know how to trace hallucinations back to weak prompts, missing guardrails, or lack of tool access and fix them.
Prototyper at heart:
Youre not scared of building from scratch and iterating fast, using open-source or hosted tools as needed.
What you must have
- 5+ years in AI/ML or voice/NLP systems with real-time experience
- Deep knowledge of
LLM orchestration
, RAG
, vector search
, and prompt engineering
- Experience with
MCP-style architectures
or structured context pipelines between LLMs and APIs/tools - Experience integrating ASR (Whisper/Deepgram), TTS (ElevenLabs/Coqui), and OpenAI/GPT-style models
- Solid understanding of latency optimization, streaming inference, and real-time audio pipelines
- Hands-on with
Python
, FastAPI
, vector DBs (Pinecone, Weaviate, FAISS), and cloud infra (AWS/GCP) - Strong debugging, logging, and QA instincts for hallucination, grounding, and UX behavior
Why Spyne?
Real-world AI impact at scale
A-Grade team that balances speed with technical depth
High autonomy and visibility from Day 1
Rapid growth = faster career acceleration
MacBook + all the tools and compute you need
Flat structure, no BS, just real work