Overview
Lead AI Engineer to join AI-augmented delivery pods and build AI solutions for complex finance and operations use cases for PE-backed clients.
What you'll do
- Propose AI solution architecture that is scalable, secure, and aligned with engineering standards.
- Build and iterate generative AI features using prompt engineering, RAG pipelines, and multi-agent workflows.
- Integrate large language models into enterprise applications with reliable data flow.
- Develop prototypes and proof of concepts and iterate based on stakeholder feedback.
- Write and execute regression evaluation suites for LLM-based features to validate output quality and consistency.
- Build observability and evaluation infrastructure and monitor AI pipelines to identify and escalate issues.
- Develop and maintain web applications using MEAN or MERN on Azure and AWS, and write clean testable code.
What you'll need
- 4-8 years of overall software development experience building production-grade applications.
- 1-2 years of hands-on experience designing and developing generative AI applications, including LLM integration and RAG pipelines.
- Experience with AI orchestration/agent frameworks and core RAG concepts including embedding models and vector databases.
- Experience with LangChain, LangGraph, AutoGen, or DSPy (or equivalent orchestration frameworks).
- Minimum 4 years with the MERN or MEAN stack and multiple deployed projects across the development lifecycle.
- Proficiency in Python for AI and SQL for data querying, with working knowledge of JavaScript/TypeScript.
- Comfort with Git/GitHub or GitLab and CI/CD pipelines, plus containerization using Docker.
Details
- Location: Hyderabad, Telangana.
Read the full description and apply on the company’s own careers page.
