Lead AI Engineer

Lead AI Engineer

We are looking for a Lead AI Engineer with 5 - 8 years of experience to design and build enterprise-grade AI applications using Large Language Models (LLMs), Voice AI and Retrieval-Augmented Generation (RAG).

The role involves developing scalable Python-based microservices, integrating AI/LLM services with enterprise applications, and building high-performance AI solutions with a focus on latency, cost, reliability and accuracy.

Key Responsibilities:

• Design and develop enterprise AI applications using Python, LLMs, RAG and Voice AI.
• Build scalable and production-ready microservices using Python, FastAPI and/or Django.
• Develop REST APIs, WebSocket-based services and asynchronous applications.
• Integrate OpenAI APIs, OpenAI SDK, GPT-4o, GPT-5, Claude and other LLM platforms.
• Develop conversational and voice AI applications using Speech-to-Text, Text-to-Speech and OpenAI Realtime API.
• Design and implement RAG pipelines using embeddings and vector databases.
• Work with technologies such as LangChain and vector databases including Pinecone, Weaviate, Qdrant or Milvus.
• Build AI assistants, workflow automation solutions and enterprise AI integrations.
• Optimize AI applications for latency, scalability, cost and response accuracy.
• Implement caching and high-performance solutions using Redis.
• Work with asynchronous programming, streaming audio and real-time AI interactions.
• Apply prompt engineering, function calling, structured outputs and JSON Schema where required.
• Implement AI safety, guardrails and model evaluation practices.
• Collaborate with product, engineering and business teams to translate requirements into production-ready AI solutions.
• Lead technical design decisions and contribute to engineering best practices.

Must-Have Skills:

• 58 years of software/AI engineering experience.
• Strong hands-on Python development experience.
• FastAPI and/or Django.
• REST APIs and microservices architecture.
• WebSockets and asynchronous programming.
• Redis.
• Hands-on experience with LLM applications.
• OpenAI APIs / OpenAI SDK.
• Experience with GPT-4o, GPT-5 and/or Claude.
• Speech-to-Text and Text-to-Speech.
• OpenAI Realtime API or similar real-time voice AI technology.
• Embeddings and vector databases.
• LangChain or equivalent LLM application framework.
• Experience building production-grade AI applications.

Good to Have:

• JavaScript / TypeScript.
• Gemini.
• Prompt Engineering.
• Function Calling and Structured Outputs.
• JSON Schema.
• Context Window Management and Token Optimization.
• AI Safety and Guardrails.
• Model Evaluation / AI Evaluation Frameworks.
• Pinecone, Weaviate, Qdrant or Milvus.
• LlamaIndex.
• Hugging Face Transformers / Sentence Transformers.
• Pydantic AI.
• Conversational AI / Voice AI.
• AI Assistants and Workflow Automation.
• MCP.
• Streaming Audio and Voice Activity Detection.

Location: Hyderabad
Work Mode: Work From Office
Experience: 5–8 Years
CTC: 15–24 LPA
Notice Period: 0–15 Days
Employment Type: Full-Time
Qualification: Bachelor's Degree
Working Hours: 10:00 AM – 7:00 PM
Openings: 1

Benefits: Group Medical Insurance

Coding Assessment: Not Applicable