Website:
Job details:
About Bricklyn
At Bricklyn, we are building next-generation, omnichannel AI assistants capable of handling complex, real-world business operations autonomously. Our core focus is on creating seamless, human-like interactions across multiple channels (Voice, text messaging, and Web) powered by state-of-the-art LLMs and advanced data architectures.
About the Role
We are looking for a highly skilled Python / AI Developer to lead the development of our core AI systems. In this role, you will build conversational AI agents that interact naturally with humans using LLMs and Voice APIs. You will be responsible for designing a robust backend that intelligently connects unstructured conversational data with structured relational data (PostgreSQL) and complex entity relationships (Neo4j).
If you are obsessed with reducing latency in voice AI, building hallucination-free RAG pipelines, and writing clean, asynchronous Python code, we want to talk to you.
Key Responsibilities
Omnichannel AI Development: Build and deploy a conversational AI agent capable of maintaining context and session memory across multiple communication channels seamlessly.
Low-Latency Voice Integration: Integrate and optimize Speech-to-Text (STT), LLMs, and Text-to-Speech (TTS) pipelines using WebSockets and async streaming to ensure ultra-low latency, natural voice conversations.
Database Architecture: Architect and maintain a dual-database backend using PostgreSQL for transactional business data and Neo4j for complex, interconnected knowledge graphs.
Advanced LLM Orchestration: Implement advanced Retrieval-Augmented Generation (RAG) and GraphRAG to ground the AI in internal documents and real-time database queries.
Function Calling & Tool Use: Design strict LLM function-calling (Tool use) workflows to fetch live database records, trigger external API alerts, and execute business logic without hallucinating facts.
Backend Engineering: Write highly concurrent, production-ready Python code utilizing frameworks like FastAPI and asyncio.
Required Skills & Qualifications
Experience: 3+ years of backend software engineering, with hands-on experience building applications using Generative AI / LLMs.
Python Mastery: Deep understanding of Python, especially asynchronous programming (asyncio), FastAPI, and handling I/O bound tasks efficiently.
AI & LLMs: Proven experience with LLM APIs (OpenAI, Anthropic, or open-source models), prompt engineering, system prompts, function calling, and frameworks like LangChain or LlamaIndex.
Voice & Audio APIs: Experience with programmatic voice and telephony platforms (e.g., Twilio, Bland AI, Retell AI, Deepgram, or ElevenLabs).
Database Proficiency:
Strong SQL skills and experience with PostgreSQL (experience with pgvector is a huge plus).
Hands-on experience with Graph databases, specifically Neo4j, and writing Cypher queries.
System Design: Strong understanding of building scalable microservices and handling API integrations.
Nice to Have (Bonus Points)
Experience implementing GraphRAG (merging knowledge graphs with LLM retrieval).
Experience with Voice Activity Detection (VAD) and handling conversational interruptions (barge-in) in real-time voice agents.
DevOps experience (Docker, AWS/GCP).
What We Offer
Competitive salary structure.
Hybrid/Remote work flexibility based out of Trivandrum.
- The opportunity to build a greenfield AI product from the ground up and shape its core architecture alongside a fast-moving team.
Click on Apply to know more.