Full Stack Developer (Python + Fast API + LLM + RAG)

Experience: 5+ Yrs

Location: Hyderabad

Notice period: Looking for Immediate Joiner.

Job Summary

We are looking for a highly motivated Senior AI Developer to design and build enterprise-grade AI applications using Large Language Models (LLMs), Voice AI, Agentic AI, Retrieval-Augmented Generation (RAG), and Multimodal AI. The ideal candidate will have strong backend development experience and hands-on expertise in integrating AI models into scalable production systems.

Roles & Responsibilities

•     Design and develop AI-powered enterprise applications using LLMs.

•     Build Voice AI solutions for real-time conversational systems.

•     Develop AI Agents capable of reasoning, planning, and tool execution.

•     Design and implement RAG pipelines using vector databases.

•     Integrate AI services with REST APIs, WebSockets, SIP, and enterprise systems.

•     Develop scalable Python microservices.

•     Optimize AI applications for latency, cost, and accuracy.

•     Build reusable AI workflows and tool-calling frameworks.

•     Collaborate with Product, QA, and DevOps teams.

•    Evaluate and integrate emerging AI technologies.

Required Technical Skills

Programming Languages

•     Python (Mandatory)

•     JavaScript/TypeScript (Preferred)

•    Database [Vector DB]

Backend Development

•     FastAPI

•     Django

•     REST APIs

•     WebSockets

•     Async Programming (asyncio)

•     Microservices

•    Redis

1. Large Language Models (LLMs)

Must have experience with:

•     OpenAI APIs (Chat Completions / Responses API)

•     GPT-4o / GPT-5 or equivalent LLMs

•     Claude

•     Gemini (Preferred)

Good understanding of:

•     Prompt Engineering

•     Function Calling / Tool Calling

•     Structured Outputs

•     JSON Schema

•     Context Window Management

•     Token Optimization

•     AI Safety

•    Model Evaluation

2. Voice AI

Hands-on experience with:

•     Speech-to-Text (STT)

•     Text-to-Speech (TTS)

•     OpenAI Realtime API (Preferred)

•     Streaming Audio

•     Voice Activity Detection (VAD)

•    Realtime WebSocket APIs

3. Retrieval-Augmented Generation (RAG)

Experience with:

•     Embeddings

•     Vector Databases

Preferred databases:

•     Redis Vector Search

•     Pinecone

•     Weaviate

•     Qdrant

•    Milvus

AI Libraries & Frameworks

Strong experience with:

•     OpenAI SDK

•     LangChain

•     LlamaIndex

•     Hugging Face Transformers

•     Sentence Transformers

•    Pydantic AI (Preferred)

Preferred Domain Experience

•     Conversational AI

•     Voice AI

•     AI Assistants

•     Customer Support Automation

•    Workflow Automation

Nice to Have

•     MCP (Model Context Protocol)

•     AI Guardrails

•     Prompt Versioning

•     Cost Optimization

•    AI Evaluation Frameworks