Description :

We are seeking a highly skilled AI Developer with deep expertise in agentic AI and modern LLM-driven solutions.

The candidate will play a pivotal role in designing, building, and deploying autonomous AI agents and intelligent systems that leverage large language models (LLMs) and retrieval-augmented generation (RAG) frameworks.

This position requires a strong foundation in Python, cloud infrastructure, vector databases, and MLOps practices, with experience in integrating cutting-edge AI frameworks for real-world applications.

Key Responsibilities :

- Design, develop, and maintain agentic AI solutions leveraging LLMs, RAG architectures, and AI orchestration frameworks.

- Integrate multiple LLMs (OpenAI, Anthropic, etc.) into scalable AI pipelines for various business use cases.

- Implement LangChain / LangGraph / AutoGen / CrewAI pipelines for autonomous agents and multi-step reasoning systems.

- Develop and maintain vector databases (Pinecone, Milvus) for efficient semantic retrieval and knowledge storage.

- Architect and deploy RAG (Retrieval-Augmented Generation) solutions for dynamic information retrieval and question-answering applications.

- Implement MLOps pipelines, containerization (Docker), and CI/CD for AI model deployment in cloud environments (AWS, GCP, Azure).

- Collaborate with cross-functional teams (Data Scientists, ML Engineers, Product Managers) to design and implement robust AI-driven solutions.

- Monitor, optimize, and scale AI systems for performance, reliability, and cost-efficiency.

- Stay current with emerging trends in LLMs, agentic AI, and AI orchestration frameworks, providing thought leadership and innovation within the team.

Mandatory Skills & Expertise :

- Python (advanced) : Strong coding skills, data structures, and algorithmic problem-solving capabilities.

- Agentic AI Frameworks : Hands-on experience with LangChain, LangGraph, AutoGen, CrewAI.

- LLM Integration : Experience integrating models from OpenAI, Anthropic, or similar providers.

- Vector Databases : Proficiency with Pinecone, Milvus, or similar vector search/storage solutions.

- RAG (Retrieval-Augmented Generation) : Designing and implementing RAG pipelines for AI applications.

- Cloud Platforms : Hands-on experience with AWS, GCP, or Azure, including deployment and management of AI workloads.

- MLOps & Containerization : Expertise in Docker, CI/CD, and AI model lifecycle management.

- Strong analytical, problem-solving, and debugging skills.

- Excellent collaboration and communication skills to work effectively in a team-oriented environment.

Preferred Skills :

- Experience with multi-agent systems and autonomous AI agents.

- Familiarity with transformers, embeddings, and vector similarity search optimization.

- Knowledge of scalable AI architectures and distributed systems.

- Exposure to prompt engineering, model fine-tuning, and custom LLM training.

Education :

- Bachelors or Masters degree in Computer Science, AI, Machine Learning, or related fields