To Apply: *https://forms.gle/G7pJQrs4wY3YrSip9
* Role Summary Design, build, and optimize production-grade Generative AI and Agentic AI systems for intelligent automation. Work across LLMs, agent orchestration, RAG, model adaptation, and scalable AI services.

Key Responsibilities

- Build agentic and multi-agent systems using Python, LLM APIs, LangGraph/LangChain, tool calling, and structured workflows.
- Develop RAG pipelines using embeddings, vector databases, semantic retrieval, reranking, and context engineering.
- Fine-tune and adapt LLMs/SLMs using SFT, LoRA/QLoRA, PEFT, and quantization where appropriate.
- Build scalable AI services and inference pipelines using FastAPI, asynchronous programming, and serving technologies such as vLLM.
- Integrate AI systems with enterprise APIs, databases, and business tools using tool calling and protocols such as MCP.
- Build evaluations and observability covering quality, hallucination,



task completion, latency, token usage, cost, and execution traces.
- Optimize accuracy, latency, throughput, memory usage, and inference cost.
- Design reliable workflows with state, memory, guardrails, validation, retries, error handling, and human oversight.
- Apply security, privacy, access-control, and responsible-AI practices.
- Turn promising experiments into production-ready systems; contribute to architecture, deployment, and engineering best practices.
- Collaborate with product, engineering, data, and domain teams to translate operational problems into AI solutions.
- Support customer engagements as needed: understand workflows, explain technical choices, and assist with integration and deployment.

📌 Artificial Intelligence Engineer (Chennai)
🏢 TNQTech
📍 Chennai