Description

You will design, develop, and deploy scalable GenAI applications and LLM-powered systems, integrating them into the broader Java-based full-stack architecture.

This role is on-site.

Responsibilities

• Build LLM-based AI agents and orchestrate autonomous workflows using LangChain, LlamaIndex, or Semantic Kernel.
• Design and implement Retrieval-Augmented Generation (RAG) architectures with vector databases like FAISS, Pinecone, or Weaviate.
• Develop and maintain data pipelines for structured and unstructured data using Python and SQL.
• Build CI/CD pipelines for AI/ML workloads, deploying services in Docker containers and Kubernetes clusters.
• Deploy and optimize AI solutions on AWS, Azure, or GCP, ensuring security, compliance, and cost-efficiency.

Required Skills

• Strong proficiency in Java and Python.
• Experience with LLMs, AI agents, and agent frameworks.
• Hands-on expertise with RAG architectures and vector databases.
• Working knowledge of SQL and data engineering concepts.
• Experience implementing CI/CD pipelines for AI or ML systems.
• Experience with containerization (Docker) and orchestration (Kubernetes).
• Proven experience with at least one major cloud platform (AWS, Azure, or GCP).
• Understanding of MLOps principles, including model versioning and monitoring.

Preferred Skills

• Experience fine-tuning LLMs using LoRA, PEFT, or RLHF.
• Familiarity with GenAI evaluation frameworks and hallucination testing.

Key Skills

Education

Bachelor's or Master's degrees