Generative AI Engineer

Job Description

(PLEASE READ THROUGH THE JD COMPLETELY BEFORE APPLYING) Job Title: AI Engineer Job Type: Full-Time | Location: Chennai / Coimbatore Experience Level: Associate (4 – 5 years) Company Overview: Yavar is a data intelligence platform company offering industry-specific private AI applications. Our platforms help enterprises unlock intelligence using a powerful blend of agentic AI applications, deep-tech orchestration, and privacy-preserving infrastructure. We’re looking for an AI Engineer to build and scale next-gen GenAI products that blend large language models, real-time inference, and intelligent automation. Who Should Apply: We are seeking engineers with 4–5 years of software development experience , including 1–2 years specifically in building GenAI applications . If you’ve worked hands-on with LLMs, embeddings, RAG pipelines, and vector databases—and you're excited about building products that leverage cutting-edge protocols like MCP—this role is for you. Familiarity with vibe coding or similar prompt-oriented dev environments is a big plus. Role Summary: As an AI Engineer at Yavar, you’ll be at the heart of building high-performance, scalable GenAI applications. You’ll work with LLMs (open and private), design fine-tuning pipelines, optimize vector search performance, and build secure agentic interfaces powered by emerging multi-agent coordination protocols (MCP). Key Responsibilities: Design, develop, and deploy LLM-powered features across Yavar’s AI platforms. Implement prompt engineering, fine-tuning, embedding generation, and vector-based retrieval strategies. Build and manage RAG pipelines using public/private LLMs, vector DBs, and contextual memory. Integrate multi-agent coordination using protocols like MCP (Multi-agent Communication Protocol). Collaborate with product, infra, and UI teams to ship end-to-end AI features at scale. Contribute to the design of secure, multi-tenant GenAI architectures with RBAC and data privacy controls. Write clean, maintainable code using vibe coding frameworks or equivalent prompt-based dev setups. Stay up to date with the latest in LLM optimization, open-weight models, and inference tuning. Participate in architecture reviews, performance benchmarking, and deployment automation. Must-Have Qualifications: 4–5 years of experience in software development (Python, Node.js, or similar modern stacks) 1–2 years of hands-on experience in GenAI, LLMs, or NLP-based applications Strong understanding of fine-tuning strategies (LoRA, PEFT, full model) Experience with embedding models, vector databases (Pinecone, ChromaDB, Weaviate, FAISS, or similar) Solid grasp of Retrieval-Augmented Generation (RAG) architecture and memory management Familiarity with multi-agent systems and emerging protocols like MCP Exposure to vibe coding, prompt-oriented frameworks, or LangChain-based development Experience in building APIs and microservices for AI workloads Bachelor's or Master’s degree in Computer Science, AI/ML, or equivalent Key Attributes: Builder’s mindset with deep curiosity for LLM behavior and tuning Pragmatic problem solver with clean coding habits Strong understanding of AI/ML pipelines and data flows Effective communicator who can explain model behavior and limitations Comfortable in fast-paced, iterative product environments Always learning and experimenting with new models and techniques Why Join Us? Shape the future of AI products used across industries Build on cutting-edge infrastructure in a secure, privacy-first AI stack Collaborate with exceptional teams across AI, product, and design Lead innovations in AI agent design, multi-agent protocols, and GenAI governance Grow with a fast-scaling company embracing deep-tech and creative engineering How to Apply: If you're passionate about building transformative AI solutions with emerging technologies, we want to hear from you. Send your resume (with Gen-AI project details and LLM-related work) to careers@yavar.ai Show more Show less