Lead GenAI / Agentic AI Engineer

Company Description

ThreatXIntel is a growing Cybersecurity, IT Staffing, and Consulting company delivering end-to-end technology and security solutions.

We are hiring for our corporate client. ThreatXIntel is the official hiring partner for this requirement.

About the Role

We are looking for experienced and passionate Generative AI / Agentic AI Engineers and Leads to join our AI Engineering team in Chennai.

The ideal candidate will have strong hands-on experience in building and deploying production-grade Generative AI and Agentic AI applications using Large Language Models (LLMs), Retrieval-Augmented Generation (RAG), AI agents, multimodal models, and enterprise-scale AI infrastructure.

You will work on next-generation AI solutions involving LLM orchestration, RAG pipelines, vector databases, model serving, AI microservices, MLOps/LLMOps, and cloud-native architectures.

Key Responsibilities

• Design, develop, and deploy enterprise-grade Generative AI and Agentic AI applications.
• Build, optimize, and scale Retrieval-Augmented Generation (RAG) pipelines.
• Design agentic workflows and multi-agent AI systems for complex enterprise use cases.
• Deploy and serve custom LLMs using vLLM, Ollama, quantization, and inference optimization techniques.
• Work with LLMs and multimodal models including GPT, LLaMA, Claude, Stable Diffusion, and DALL·E.
• Develop AI workflows using LangChain, LlamaIndex, Hugging Face, OpenAI APIs, Anthropic, AutoGen, and related frameworks.
• Build embedding pipelines, semantic search, hybrid search, reranking, and advanced retrieval solutions.
• Implement vector database solutions using Pinecone, Weaviate, ChromaDB, FAISS, or Milvus.
• Develop scalable REST APIs, GraphQL services, Kafka-based services, and AI microservices.
• Deploy AI workloads on AWS, Azure, or GCP using Docker and Kubernetes.
• Implement enterprise MLOps/LLMOps practices, including CI/CD, testing, monitoring, observability, and model lifecycle management.
• Apply Prompt Engineering, PEFT, LoRA, and QLoRA techniques for model adaptation and optimization.
• For Lead roles, provide technical leadership, architecture guidance, code reviews, and mentorship to AI engineering teams.

Required Skills

• Strong hands-on programming experience in Python.
• Proven experience building Generative AI and/or Agentic AI applications.
• Hands-on experience with GPT, LLaMA, Claude, or similar Large Language Models.
• Experience with LangChain, LlamaIndex, Hugging Face, OpenAI APIs, Anthropic, or AutoGen.
• Strong understanding of RAG architecture, embeddings, chunking strategies, semantic search, hybrid search, and reranking.
• Experience with vector databases such as Pinecone, Weaviate, ChromaDB, FAISS, or Milvus.
• Knowledge of vLLM, Ollama, model quantization, and LLM deployment/inference optimization.
• Experience with Docker, Kubernetes, and AWS/Azure/GCP.
• Familiarity with REST APIs, GraphQL, Kafka, and microservices architecture.
• Working knowledge of PyTorch or TensorFlow.
• Understanding of enterprise MLOps and LLMOps practices.

Preferred Qualifications

• Experience building and scaling production-grade AI platforms or GenAI products.
• Hands-on experience with multimodal AI applications.
• Experience with Prompt Engineering, PEFT, LoRA, and QLoRA.
• Knowledge of CI/CD pipelines, AI observability, model monitoring, and evaluation frameworks.
• Experience designing secure and scalable enterprise AI architectures.

Selection Process

1. HR Interview
2. Online Coding Round
3. Online Technical Interview
4. Final In-Person Interview – Chennai Office

Additional Information

Location: Chennai

Work Mode: 100% Work from Office – 5 Days a Week

Employment Type: Full-time

Notice Period: 0–15 Days – Immediate Joiners Preferred

If you are passionate about building next-generation Generative AI and Agentic AI systems and want to work on cutting-edge, production-scale AI solutions, we would love to hear from you.