Description

Design and implement LLM workflows, retrieval-augmented generation pipelines, and vector store integrations to deliver accurate and safe AI outputs.

This role is on-site.

Responsibilities

• Build and optimize Python-based AI components, including embedding generation, model orchestration, evaluation scripts, and automation tools.
• Architect and deploy AI solutions on AWS, ensuring performance, cost efficiency, and secure data access.
• Develop prompt templates, guardrails, evaluation metrics, and safety checks to reduce hallucinations and improve model reliability.
• Collaborate with data engineering teams to prepare high-quality datasets and ensure reliable data pipelines for model training.
• Conduct testing and validation of AI systems, covering retrieval quality, model accuracy, latency, and user experience.

Required Skills

• 9+ years of software engineering experience.
• Strong proficiency in Python for building AI components and automation tools.
• Hands-on experience with LLMs, prompt engineering, and RAG architectures.
• Experience deploying and managing services on AWS.
• Knowledge of vector stores and embedding generation.
• Ability to design evaluation metrics and safety guardrails for AI models.
• Java experience is required.

Preferred Skills

• Experience collaborating with data engineering teams on transformation logic and data pipelines.
• Background in documenting AI architectures and supporting governance practices.

Key Skills

Education

Any Gradute