Lead AI Engineer

Hiringhood; Hyderabad; On-site; INR 1,200,000 - 2,400,000; Full time

Job summary

Hiringhood is seeking an experienced AI/Backend Engineer in Hyderabad to design and build AI-powered enterprise applications using LLMs and voice AI. You will implement RAG pipelines, integrate with REST APIs and streaming services, and develop scalable Python microservices.

Candidates should have hands-on experience with OpenAI APIs, vector databases, and modern AI tooling. Join a collaborative team focused on performance, safety, and continuous improvement.

Qualifications

• Python is mandatory for core development.

Responsibilities

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

Skills

Python

JavaScript/TypeScript

Vector DB

Redis

FastAPI

Django

REST APIs

WebSockets

Async programming

Microservices

OpenAI APIs

GPT-4o / GPT-5

Claude

Gemini

Prompt Engineering

Tool Calling

JSON Schema

Context Window Management

Token Optimization

AI Safety

Model Evaluation

Speech-to-Text

Text-to-Speech

Embeddings

Vector Databases

OpenAI SDK

LangChain

LlamaIndex

Hugging Face Transformers

Sentence Transformers

Pydantic AI

Tools

OpenAI SDK

LangChain

LlamaIndex

Hugging Face Transformers

Sentence Transformers

Pydantic AI

Job description

Job Description:

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.

Must have

Programming Languages

• Python (Mandatory)
• JavaScript/TypeScript (Preferred)
• Database [Vector DB & Redis]

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
• 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

• OpenAI SDK
• LangChain
• LlamaIndex
• Hugging Face Transformers
• Sentence Transformers
• Pydantic AI

Preferred Domain Experience

• Conversational AI
• Voice AI
• AI Assistants
• Customer Support Automation
• Workflow Automation

Good to have

• MCP (Model Context Protocol)
• AI Guardrails
• Prompt Versioning
• Cost Optimization
• AI Evaluation Frameworks

Requirements: