Overview
Develop, implement and enable reusable AI-agent products and capabilities across the Central Development Platform Team and the Central Test Team, turning development and testing use cases into production-ready, governed AI solutions.
What you'll do
- Design and implement production-grade AI agents and reusable workflows using LLMs, tool calling, prompt/context engineering, RAG, APIs, and structured outputs.
- Build secure Python services, connectors, retrieval capabilities, templates, and guardrails that integrate with approved engineering tools, repositories, pipelines, and knowledge sources.
- Develop AI agents and solutions for requirements, coding, documentation, engineering knowledge retrieval, developer support, and workflow automation.
- Develop AI agents and accelerators for test planning, design, automation, test data, impact analysis, prioritization, defect insights, and quality reporting.
- Integrate solutions with test frameworks and delivery pipelines, and establish evaluations for groundedness, factual consistency, robustness, latency, security, and response quality.
- Integrate reusable AI services into development platforms and CI/CD workflows, providing scalable, observable, secure, and cost-aware self-service experiences.
- Apply responsible-AI, data-protection, access-control, prompt-injection, auditability, and human-oversight guardrails while optimizing reliability and cost.
- Partner with development, testing, platform, architecture, security, and product stakeholders to identify valuable use cases, industrialize successful solutions, enable adoption, and maximize reuse.
- Implement monitoring and observability for AI agents to continuously improve reliability and performance.
- Evolve successful AI use cases from prototypes into reusable, scalable platform products.
- Measure the value and adoption of AI solutions through productivity, quality, automation, and usage outcomes.
- Support in enabling development and test teams through reusable patterns, documentation, coaching, and self-service capabilities.
What you'll need
- 2+ years in software engineering, AI/ML, quality engineering, test automation, or data, including hands-on delivery responsibility.
- Degree in Computer Science, Software Engineering, AI/Data Science, Information Technology, or a comparable qualification.
- Hands-on Python and API/service development experience, with a strong understanding of software architecture, the SDLC, cloud, containers, Git, CI/CD, and observability.
- Practical experience with GenAI/LLM solutions, including prompt engineering, RAG, embeddings, agent workflows, tool calling, structured outputs, and AI evaluation.
- Understanding of development platforms and quality engineering, including automated testing, API testing, test automation, and quality gates.
- Strong analytical, product, documentation, and collaboration skills, with professional proficiency in English.
Nice to have
- Experience with relevant AI frameworks or cloud AI services, vector/semantic search, internal developer platforms, or testing tools.
Details
- Location: Bangalore, India.
Read the full description and apply on the company’s own careers page.