AI Engineer / Architect

IndiaNIC; Ahmedabad District; Presencial; INR 1 500 000 - 2 800 000; Tempo integral

Resumo da oferta

IndiaNIC is seeking an experienced professional to design and build internal AI solutions that boost engineering productivity and software delivery. You will work on AI-powered developer workflows, agentic SDLC automation, and reusable patterns across teams.

Collaborating with senior architects and engineering leaders, you will enable scalable AI adoption, deliver playbooks and templates, and support proof-of-concept efforts to mature into repeatable practices.

Responsabilidades

• Design and build internal AI solutions for engineering productivity and software delivery.
• Develop AI-powered developer workflows and assistants.
• Create reusable prompts, tool-calling patterns, and workflow templates.
• Partner with architects to establish scalable AI enablement patterns.
• Support offices hours, workshops, and internal enablement sessions.

Conhecimentos

AI workflows

LLM & RAG

Agentic workflows

Documentation patterns

Ferramentas

SDKs

Tool-calling

Evaluation & governance

Descrição da oferta de emprego

Internal AI Solution Development

Design and build internal AI solutions that support engineering productivity and software delivery, including:

• AI-powered developer workflows and assistants
• Agentic SDLC automation patterns
• Internal tools for code analysis, documentation, testing, migration, and engineering support
• Reusable prompt, tool-calling, and workflow patterns
• Reference implementations that can be adopted by engineering teams

Develop solutions that are practical, scalable, maintainable, and aligned with RealPage engineering standards.

Agentic Workflow and Platform Enablement

Build reusable capabilities that help teams adopt AI consistently across the organization, including:

• Multi-step agentic workflows
• Tool-calling and orchestration patterns
• RAG-based internal knowledge solutions
• Shared SDKs, templates, and integration examples
• Reusable components for copilots, agents, and AI-enabled engineering workflows

Partner with senior architects and engineering leaders to establish patterns that can scale beyond one team or use case.

Engineering Team Enablement

Work directly with engineering teams, champions, and internal stakeholders to help them adopt AI effectively. Responsibilities include:

• Pairing with teams on AI use cases and implementation patterns
• Providing technical guidance on LLM, RAG, and agentic workflow design
• Supporting proof-of-concept efforts and helping mature them into repeatable practices
• Creating playbooks, examples, templates, and documentation for internal engineering use
• Participating in office hours, workshops, and AI enablement sessions

AI Evaluation, Quality, and Responsible Use

Help define and apply practical evaluation and governance practices for internal AI solutions, including:

• Prompt and workflow evaluation
• Accuracy, relevance, and usefulness testing
• Safety and responsible AI considerations
• PII and sensitive-data handling
• Logging, observability, and feedback loops
• Human-in-the-loop review patterns where appropriate

Ensure internal AI solutions are developed with quality, security, privacy, and reliability in mind.

Delivery and Cross-Functional Collaboration

Partner with engineering leadership, product teams, architecture, security, and other stakeholders to identify and deliver high-impact AI use cases. Responsibilities include:

• Translating engineering productivity needs into AI-enabled solutions
• Supporting roadmap-aligned internal AI initiatives
• Contributing to adoption and capacity-improvement goals
• Helping measure the impact of AI enablement efforts
• Communicating technical concepts clearly to engineering and non-engineering audiences

Performance, Reliability, and Cost Awareness

Design AI solutions with practical performance and cost considerations, including:

• Model selection and routing
• Prompt and context optimization
• Caching and retrieval efficiency
• Latency and reliability considerations
• Build-vs-buy recommendations
• Avoidance of vendor lock-in where practical