Job Title: - AI Engineer

Location: Bangalore, Chennai
Experience: 3-7 years.
Notice Period: Immediate to 45 days Max.

We are looking for an AI Engineer with 3 to 5 years of experience to design, build, and deploy scalable AI-powered applications, Large Language Models (LLMs), and Agentic AI frameworks. In this role, you will focus on building intelligent systems, creating production ready APIs, and deploying cloud-hosted AI solutions. You will collaborate with cross -functional teams to translate emerging generative AI techniques into reliable, business-driven products.

Key Responsibilities:

Agentic AI LLM Development

- Build, evaluate, and optimize AI agents using frameworks such as LangChain, LangGraph, CrewAI, or AutoGen.

- Implement agentic workflows, multi-agent orchestration, tool integration, state management, and multi-step reasoning patterns (e.g., ReAct).

- Design robust Retrieval-Augmented Generation (RAG) pipelines, prompt tuning strategies, and context management systems.

- Integrate, fine-tune, or adapt both open-source (e.g., LLaMA, Phi) and commercial foundation models (e.g., GPT-4,Claude).Deployment MLOps

- Package AI models and agentic workflows into production-ready REST APIs.

- Containerize and deploy solutions using Docker and Kubernetes across cloud platforms (AWS, Azure, or GCP).

- Establish MLOps pipelines covering model tracking, automated deployment (CI/CD), observability, and vector database management.

- Optimize system latency, token usage,



and infrastructure cost for production workloads.Cross-Functional Collaboration

- Work alongside product managers, data scientists, and backend engineers to integrate AI capabilities into application ecosystems.

- Conduct experiments to evaluate new AI tools, frameworks, and model architecture updates.

Skills Qualifications

Required

- AI LLM Stack: Robust proficiency in Python, SQL, and GenAI frameworks (LangChain,LangGraph, CrewAI, AutoGen).

- Agentic Design: Hands-on experience building agents with tool-calling capabilities, memory retention, guardrails, and structured outputs.

- Retrieval Data: Solid understanding of RAG architectures, embedding models, prompt engineering, and vector databases (e.g., Pinecone, Qdrant, Chroma, Weaviate).

- API Integration: Experience building REST APIs (e.g., FastAPI) and moving data across external APIs and SQL databases.

- Cloud DevOps: Practical experience with Docker, container management, and cloud infrastructure (AWS, Azure, or GCP).

Preferred

- 3+ years of focused experience building and shipping LLM applications or agents in production settings.

- Familiarity with AI observability and evaluation tools (e.g., LangSmith, Phoenix, MLflow).

- Demonstrable portfolio, open-source contributions, or GitHub projects focused on AI agent development

Disclaimer: This job posting has been aggregated from external source. Role details, content, and availability are subject to change. Applicants are advised to confirm the latest information directly on the company website before applying.

📌 AI Engineer (Chennai)
🏢 Pi Square Technologies
📍 Chennai