Generative AI Engineer

Overview

Job Title: Generative AI Engineer

Location: Coimbatore

Employment Type: Full-Time

Experience: 2+ Years

About the Company

Splixon is hiring for Yavar AI, it is an enterprise AI company offering service-as-a-software with powerful pre-built agentic platforms. We help organizations reinvent workflows, automate complex use cases, and derive clarity from data—while ensuring privacy, security, and verifiability at every layer.

We are looking for a Generative AI Engineer to build and scale next-generation GenAI products combining large language models, real-time inference, and intelligent automation.

Who Should Apply

This role is ideal for engineers with direct experience building GenAI applications. If you have hands-on expertise with LLMs, embeddings, RAG pipelines, vector databases, and enjoy building advanced AI products using emerging frameworks and protocols like MCP, you’ll thrive here. Exposure to vibe-coding or similar prompt-oriented development frameworks is a strong plus.

Role Overview

As a Generative AI Engineer at Yavar, you will play a central role in designing, developing, and scaling high-performance GenAI workflows. You will work across LLM fine-tuning, RAG architecture, vector search optimization, and agentic automation. You will collaborate closely with product, infrastructure, and UI teams to ship reliable end-to-end AI features.

Key Responsibilities

• Develop and deploy LLM-powered capabilities across Yavar’s enterprise AI platforms.
• Implement prompt engineering, fine-tuning (LoRA/PEFT/full-model), embeddings, and vector-based retrieval strategies.
• Build and optimize RAG pipelines using public/private LLMs, vector databases, and contextual memory.
• Integrate and scale multi-agent coordination using protocols like MCP (Multi-agent Communication Protocol).
• Work cross-functionally with product, infra, and design teams to ship production-grade AI features.
• Write clean, maintainable code using vibe coding frameworks or equivalent prompt-based development setups.
• Stay current with the latest developments in LLM optimization, open-weight models, inference tuning, and AI tooling.

Must-Have Qualifications

• Strong experience in software development (Python, Node.js, or similar).
• Hands-on experience with GenAI, LLMs, or NLP-driven applications.
• Deep knowledge of fine-tuning frameworks: LoRA, PEFT, or full-model training.
• Experience with embedding models and vector databases (e.g., Pinecone, ChromaDB, Weaviate, FAISS).
• Solid understanding of Retrieval-Augmented Generation (RAG) architecture and memory systems.
• Familiarity with multi-agent systems and protocols like MCP.
• Experience with vibe coding, prompt-oriented development, or LangChain-based frameworks.
• Ability to build APIs and microservices for AI applications.
• Bachelor’s or Master’s degree in Computer Science, AI/ML, or equivalent.

Key Attributes

• Builder’s mindset: curious, experimental, and deeply passionate about LLM behavior.
• Strong AI/ML pipeline understanding and ability to reason about data flows.
• Clean coder with an eye for pragmatic problem-solving.
• Strong communicator capable of explaining model behaviors clearly.
• Comfortable in fast-paced, iterative product environments.
• Always learning and staying updated with new GenAI techniques.

Why Join Us

• Work on the future of GenAI products across diverse business domains.
• Build using cutting-edge, privacy-first enterprise AI infrastructure.
• Collaborate with top-tier teams across engineering, AI research, and product design.
• Contribute to advancements in AI agents, multi-agent protocols, and GenAI governance.
• Grow with a fast-scaling, deep-tech engineering organization