RAG Backend Engineer – AI/ML Systems

Company Description:

Onelab Ventures is a leading technology company that specializes in custom AI agent solutions and software development. We collaborate with startups and enterprises to transform innovative ideas into scalable, intelligent systems that drive growth and efficiency.

Our team of AI specialists, developers, designers, and product managers has delivered over 100+ successful projects, impacting ~1 million weekly active users across sectors including SaaS, Fintech, and Healthcare. Leveraging agile methodologies and advanced AI frameworks, we ensure every product is reliable, efficient, and user-centric.

Role Description:

This is a full-time, on-site role based in Pune.

We are seeking a highly skilled Backend RAG (Retrieval-Augmented Generation) Engineer to design, develop, and maintain RAG-based systems powering intelligent enterprise solutions. You will work within an existing framework, take ownership of core modules, and integrate AI with real-world business tools like CRMs, HubSpot, and internal systems.

This role involves deploying Model Context Protocol (MCP) servers, working within an event-driven, horizontally scalable architecture, and balancing rapid prototyping with production-ready engineering.

Key Responsibilities:

• Build and maintain Retrieval-Augmented Generation (RAG) pipelines
• Take ownership of key modules within a custom RAG framework
• Deploy and manage MCP (Model Context Protocol) servers
• Integrate AI with enterprise tools like HubSpot, CRMs, email systems, and internal APIs
• Work with event-driven, horizontally scalable backend architectures
• Rapidly prototype while ensuring clean, maintainable, production-grade code
• Contribute to evolving system design and data architecture

Technical Skills Required: Primary Must-Haves:

• Hands-on experience with LlamaIndex (preferred over LangChain) for RAG pipeline development
• Built or maintained RAG systems integrating 10–12+ heterogeneous data sources
• Familiar with automation and building AI-driven workflows that generate actionable insights
• Integration experience with CRM systems (e.g., HubSpot), email platforms, and enterprise APIs
• Strong foundation in scalable backend development and cloud deployment (AWS/GCP)

Bonus/Nice to Have:

• Experience working with event-driven architectures
• Familiarity with microservices, Docker, Kubernetes, Redis
• Exposure to AI product engineering, LLM fine-tuning, or custom AI agents

Work Details:

Location: On-site – Pune Office
Type: Full-TimeJoin Date: Immediate joiners preferred

Experience 1-4 year

Job Type: Full-time

Pay: ₹590,000.00 - ₹800,000.00 per year

Benefits:

• Health insurance
• Provident Fund
• Work from home

Ability to commute/relocate:

• Hinjewadi, Pune, Maharashtra: Reliably commute or planning to relocate before starting work (Preferred)

Application Question(s):

• Have you built a RAG pipeline using Llama Index? Please describe briefly.
• How many types of data sources have you integrated into a single RAG system?
• Have you deployed Model Context Protocol (MCP) servers in production?
• What CRMs or business tools have you connected with your backend systems?
• Do you have experience working with event-driven or horizontally scalable backend architectures?
• Which cloud platforms and deployment tools are you most comfortable with?
• Are you available to attend the final in-person interview at our Pune office?
• What your Current CTC?
• What your expected CTC?
• What your notice period?

Experience:

• RAG: 2 years (Preferred)
• LlamaIndex: 2 years (Preferred)
• Model Context Protocol: 2 years (Preferred)

Work Location: In person