Responsibilities
- Serve as a senior engineer in an agile environment, delivering robust generative AI systems on schedule while adhering to business goals and iterative development principles.
- Create AI-driven QA utilities for generating test cases, synthesizing test data, automating defect analysis, summarizing logs or anomalies, and supporting code and test reviews to boost both quality and development pace.
- Build modular generative AI components, libraries, and internal assistant tools that enhance productivity across engineering, testing, and operations functions.
- Convert business and technical requirements into well-structured, maintainable Python applications using secure coding standards, design patterns, and modern LLM frameworks such as retrieval-augmented generation, tool integration, and agent architectures.
- Develop and manage large language model applications on AWS platforms, leveraging services like Amazon Bedrock, SageMaker, Lambda, ECS/EKS, API Gateway, S3, DynamoDB, and OpenSearch.
- Define standardized approaches for prompt engineering, retrieval-augmented generation, system evaluation, monitoring, and ongoing optimization of generative AI solutions.
- Advocate for ethical and secure AI practices, including safeguards, protection of personally identifiable information, model governance, reduction of hallucinations, and compliance with regulatory and security standards.
- Partner with cross-functional teams including QA, software development, architecture, product, and security to design, implement, test, and deploy AI-enhanced software solutions.
- Support and improve development workflows by promoting continuous integration, delivery, assessment, and refinement specific to generative AI systems.
- Produce clear, concise documentation covering prompts, models, datasets, codebases, workflows, and system designs to ensure knowledge transfer and long-term maintainability.
Work Arrangement
Hybrid — Hyderabad
