Key Responsibilities
Design and implement scalable AI applications, advanced Retrieval-Augmented Generation (RAG) pipelines, and multi-agent systems.
Write clean, optimized, and maintainable Python code using frameworks like FastAPI or Flask to expose AI capabilities via robust APIs.
Apply traditional machine learning techniques for data preprocessing, feature engineering, embeddings optimization, and model evaluation/fine-tuning.
Architect and manage cloud infrastructure (AWS/Azure/GCP) to deploy, monitor, and scale AI workloads using Docker, Kubernetes, or serverless services.
Manage high-performance vector databases (e.g., Pinecone, Milvus, Qdrant) and design productive data ingestion pipelines.
Mentor junior engineers, conduct code reviews, define engineering best practices, and collaborate with cross-functional product teams.

Required Skills & Qualifications
Expert-level proficiency in Python and standard backend development patterns.




Deep hands-on experience with LLM orchestration frameworks (LangChain, LlamaIndex, or Haystack) and commercial/open-source models (OpenAI, Anthropic, Llama).
Solid understanding of ML fundamentals, evaluation metrics, and frameworks like PyTorch, Hugging Face, or Scikit-Learn.
Experience deploying applications on AWS (SageMaker, Bedrock, ECS), Azure (OpenAI Service, AKS), or GCP (Vertex AI, GKE).
Solid knowledge of both traditional databases (SQL/NoSQL) and vector databases.
Familiarity with CI/CD pipelines, containerization (Docker), and model monitoring tools.

Preferred Qualifications
Experience with fine-tuning open-source LLMs or optimizing context windows.
Understanding of AI safety, guardrails, and cost-optimization strategies for LLM tokens.

📌 Gen Ai Developer Chennai
🏢 Tech Mahindra
📍 Chennai