About the Role

Vector & Voice is an engineering and digital growth studio building high-performance systems and real-world AI applications. We solve operational bottlenecks for businesses by replacing manual workflows with autonomous conversational agents, intelligent pipelines, and enterprise data retrieval systems.

We are seeking an AI Lead Architect to take end-to-end ownership of our AI engineering track. You will architect, prototype, deploy, and scale production-ready LLM applications, custom RAG (Retrieval-Augmented Generation) pipelines, and autonomous agents integrated directly into client software environments (WhatsApp APIs, internal CRMs, and web platforms).

This is not a theoretical research role. We are looking for a systems builder who can write production-grade code, integrate vector databases, optimize token latency/cost, and take systems live on real enterprise traffic.

Key Responsibilities

- Agent & Workflow Architecture: Design and deploy multi-turn conversational AI agents, task-routing bots, and autonomous workflows capable of handling structured actions, scheduling, and qualified lead intake.
- Enterprise RAG Systems: Architect scalable Retrieval-Augmented Generation (RAG) pipelines over unstructured enterprise documentation, internal databases, and private client knowledge bases using vector embeddings and hybrid search.
- Third-Party & API Integrations: Build robust, fault-tolerant backend connectors linking LLM engines to external APIs, WhatsApp Cloud API/Twilio, Supabase/PostgreSQL, webhooks, and client CRMs.
- Performance & Cost Optimization: Implement strict caching mechanisms, prompt engineering, context window management, and fallback routines to maintain sub-second response latency and low inference costs.




- Production Guardrails & Reliability: Establish structured output schemas (JSON-mode / function calling), evaluation frameworks, data privacy boundaries, and guardrails against hallucinations.
- Technical Ownership: Lead the AI product lifecycle from technical scoping and schema design to Dockerized deployment, cloud hosting, and post-launch maintenance SLAs.

Requirements & Technical Qualifications

- Core AI/LLM Experience: 2+ years of hands-on production experience building with modern LLM orchestration frameworks (LangChain, LlamaIndex, or raw API tool-calling/function-calling pipelines).
- Backend Proficiency: Solid background in Python (FastAPI, Flask) or Node.js/TypeScript for building high-throughput REST APIs and webhook listeners.
- Database & Vector Infrastructure: Practical working knowledge of relational/NoSQL databases (PostgreSQL/Supabase) and vector stores (pgvector, Pinecone, Qdrant, or Chroma).
- Enterprise API Experience: Demonstrated experience integrating messaging APIs (WhatsApp Business API / Meta Cloud API) and third-party SaaS webhooks.
- Deployment & Cloud: Familiarity with containerization (Docker), cloud deployment (AWS, GCP, or DigitalOcean), and API monitoring.
- Portfolio / Work Proof: A GitHub repository, live app demo, or technical case study detailing a functional AI application or agent pipeline built by you is mandatory for consideration.
- Location: Must be located in or willing to commute to Thiruvananthapuram, Kerala.

Pay: ₹45,000.00 - ₹55,000.00 per month

Benefits:

- Paid sick time

Ability to commute/relocate:

- Sasthamangalam, Thiruvananthapuram, Kerala: Reliably commute or planning to relocate before starting work (Required)

Experience:

- Professionalism: 2 years (Required)

Work Location: In person

📌 AI Lead Architect (India)
🏢 Vector & Voice Creative Agency
📍 India