Description

Responsibilities

• Implement Generative AI based solutions using Infosys and Industry standard tools and platforms
• Implement prompt engineering techniques to evaluate model behavior under various input conditions and refining prompts for better accuracy and desired results.
• Architect end-to-end Generative AI systems, including data pipelines, model selection, orchestration, evaluation, and deployment patterns using Infosys and industry-standard tools and platforms.
• Design and implement ML/AI solutions using Python (or other relevant Data Science/AI languages), applying strong software engineering practices for maintainability, performance, and reliability.
• Build MCP and agentic-based solutions using appropriate frameworks, enabling tool/function calling, workflow orchestration, and multi-step reasoning patterns aligned to business needs.
• Test and validate GenAI applications using relevant tools and frameworks; capture, analyze, and report standard and custom quality metrics (e.g., relevance, groundedness, toxicity, latency, cost) and drive continuous improvement.
• Explore and evaluate new technologies, tools, and testing methodologies to improve development processes and solution quality; stay up-to-date with advancements in Generative AI and evaluation practices.

Technical requirement (Optional)

• Hands-on experience with LLM application patterns such as RAG, tool/function calling, prompt engineering, and automated evaluation frameworks.
• Strong MLOps/LLMOps expertise: experiment tracking, model registry, CI/CD, observability, drift detection, and incident response for AI services.
• Experience with data engineering concepts (feature stores, batch/stream processing) to support ML and GenAI workloads.
• Proven ability to lead architecture governance, create reference architectures, and drive adoption across teams and portfolios

Key Skills

Education

Bachelor's degree