Generative AI Engineer

*** Please read through the profile and apply only if your experience matches to the requirement. We need profiles with a maximum of 6 years experience only.****

Job Title: Gen-AI Engineer

Job Type:
Full-Time |
Location:
Chennai

Experience Level:
Associate (5– 6 years)

Company Overview:

Yavar is an enterprise AI company delivering service-as-a-software with pre-built agentic platforms. We help organizations reinvent workflows, automate complex use cases, and achieve clarity with data—while ensuring privacy, security, and verifiability. 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're looking for engineers with
5–6 years of strong software development experience
, including
1–2 years hands-on in GenAI application development
. You should have practical exposure to working with
LLMs/SLMs, fine-tuning, embeddings, vector databases, and RAG pipelines
, and be eager to apply them in real-world, enterprise-ready products. If you're curious about
agentic AI architectures
, excited to explore
emerging protocols like MCP
, and comfortable experimenting in
vibe coding or other prompt-driven development environments
, you'll thrive in this role.

Role Summary:

As an AI Engineer at
Yavar
, you will be at the core of building our next-generation private AI platforms. Your role will involve working with both public and private LLMs/SLMs, fine-tuning and optimizing models (including quantization and selection), and designing intelligent retrieval and multi-agent systems. You will develop context-aware, memory-driven pipelines, leverage vector databases, and implement agentic architectures powered by emerging multi-agent coordination protocols (MCP). This is a hands-on role where you will shape the intelligence layer of our platforms and deliver enterprise-ready GenAI capabilities.

Key Responsibilities

• LLM/SLM Engineering
  : Work with open-weight and private models; design and implement fine-tuning and parameter-efficient training pipelines; evaluate and select optimized or quantized models for production use.
• RAG Development
  : Build and deploy retrieval-augmented generation (RAG) pipelines, including agentic RAG setups, contextual memory, and vector-based retrieval strategies.
• Agentic Architectures
  : Integrate multi-agent coordination using protocols such as MCP; design agentic interfaces that support modular reasoning and collaborative task execution.
• Context & Memory Engineering
  : Develop caching, embeddings, and long-term memory mechanisms to improve context retention and response quality.
• Optimization & Performance
  : Conduct inference optimization, latency reduction, and benchmarking for large- and small-scale models in production.
• Coding & Orchestration
  : Write clean, maintainable code using modern frameworks and vibe-coding principles; build orchestration flows that align with product requirements.
• Collaboration & Integration
  : Work closely with product, infrastructure, and design teams to ship secure, scalable, and user-centric AI features.
• Continuous Learning
  : Stay ahead of advancements in open-weight LLMs, SLMs, embeddings, and multi-agent systems; evaluate and adopt emerging tools and standards into the Yavar ecosystem.

Must-Have Qualifications:

• 5–6 years of software development experience using modern stacks (Python, react, , go)
• 1–2 years of hands-on experience in GenAI, LLMs, or NLP-based applications
• Practical knowledge of fine-tuning methods (LoRA, PEFT, full-model tuning)
• Strong experience with embeddings and vector databases (Pinecone, ChromaDB, Weaviate, FAISS etc.,)
• Solid understanding of RAG architecture, contextual memory and caching strategies.
• Familiarity with multi-agent frameworks and emerging protocols like MCP
• Exposure to vibe coding, prompt-oriented frameworks, or LangChain-like frameworks.
• Experience building and deploying 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