About the Role

We are looking for a passionate AI Engineer with 37 years of experience to design, build, and deploy AI-powered systems. The ideal candidate should have hands-on experience with Retrieval-Augmented Generation (RAG), Agentic AI frameworks, and multi-agent systems, along with strong backend engineering expertise.

You will work on building intelligent applications that leverage LLMs, autonomous agents, and scalable infrastructure to deliver production-grade AI solutions.

Key Responsibilities

- Design and implement AI-powered applications using LLMs and modern AI frameworks
- Build and optimize Retrieval-Augmented Generation (RAG) pipelines
- Develop and orchestrate Agentic AI workflows and multi-agent systems
- Integrate LLMs with backend services, APIs, databases, and vector stores

- Develop scalable backend systems
- Optimize prompts, system design, and inference pipelines for performance and cost
- Deploy AI solutions to production environments (cloud-native preferred)
- Monitor, evaluate, and improve AI system performance
- Collaborate cross-functionally with product, design, and engineering teams

Required Skills Qualifications

- 27 years of software engineering experience
- Strong proficiency in Python (preferred) or Node.js/TypeScript
- Hands-on experience with:
- Retrieval-Augmented Generation (RAG)
- Vector databases (e.g., Pinecone, Weaviate, FAISS, Milvus)
- Agent frameworks (LangChain, LlamaIndex, AutoGen, CrewAI, etc.)




- Multi-agent orchestration systems

- Experience integrating and working with LLM APIs (OpenAI, Anthropic, open-source models)
- Solid backend experience (FastAPI, Django, Express, microservices) OR

Strong frontend experience (React, Next.js, AI-integrated UX systems)

- Understanding of embeddings, prompt engineering, evaluation techniques
- Experience deploying applications on AWS/GCP/Azure. AWS prefered
- Good understanding of system design and scalable architectures

Positive to Have

- Experience building or integrating Voice AI stacks

- Speech-to-Text (Whisper, Deepgram, etc.)
- Text-to-Speech (ElevenLabs, Azure TTS, etc.)

- Real-time streaming pipelines
- Conversational voice agents

- Experience fine-tuning or working with open-source LLMs
- Experience with monitoring LLM performance and guardrails

- Knowledge of CI/CD and DevOps practices
- Experience building AI products in production environments

What Were Looking For

- Strong problem-solving and system-thinking mindset

- Ability to rapidly prototype and iterate AI solutions
- Product-oriented thinking
- Ownership mindset and ability to work in fast-paced environments

Disclaimer: This job posting has been aggregated from external source.

Role details, content, and availability are subject to change. Applicants are advised to confirm the latest information directly on the company website before applying.

📌 Lead AI Engineer (Bengaluru)
🏢 LeadSquared
📍 Bengaluru