Job Title:- GenAI Architect
Location:- Noida/Gurugram
Job description:
What You'll Own
- Lead all things GenAI from LLM strategy and experimentation to production deployment and optimization.
- Lead the development of multi-agent systems that collaborate, reason, and learn.
- Design and own multi-agent LLM workflows, RAG pipelines, auto-evaluators, and structured generation.
- Work cross-functionally with product, backend, and infra teams to ship real AI features not demos.
- Evaluate and integrate models (OpenAI, Claude, Mistral, local LLMs), and design robust prompting strategies.
- Build reusable systems for prompt versioning, model benchmarking, latency optimization, and failure handling.
- Mentor engineers in LLM application design
You'll thrive if you:
- Have 8+ years of engineering/ML experience, with 3+ years focused on GenAI/LLMs.
- Have led or architected LLM-heavy systems used in production (ideally customer-facing).
- Have built RAG systems, prompt chains, eval loops, or intelligent automation using LLMs.
- Experience in developing multi-agent systems and orchestration logic.
- Proficiency in Python and popular AI frameworks (e.g., LangChain, OpenAI, Hugging Face, AutoGen, etc.).
- Deep understanding of LLMs and how to adapt them to different tasks.
- Love shipping fast but with depth, precision, and measurable quality.
Nice to Have:
- Experience with reinforcement learning or fine-tuning large models.
- Contributions to open-source AI/agent-related projects.
Key Responsibilities:
- Design, develop, and deploy advanced AI agents capable of handling complex tasks.
- Lead the development of multi-agent systems that collaborate, reason, and learn.
- Apply prompt engineering techniques to optimize LLM-based outputs for real-world applications.
- Collaborate cross-functionally to integrate AI solutions into larger systems and workflows.
- Perform backend/frontend/full stack development for sophisticated cloud applications
- Stay current with the latest developments in AI/ML, LLMs, agent frameworks, and research papers.
- Rapidly prototype and iterate on new ideas and agent capabilities.
Requirements:
- Demonstrated expertise in AI agent development, including hands-on experience building and running production-ready AI agents.
- Strong knowledge of prompt engineering principles and best practices.
- Proven track record of backend/frontend/full stack development
- Ability to work independently, solve ambiguous problems, and drive innovation.
Nice to Have:
- Experience with reinforcement learning or fine-tuning large models.
- Contributions to open-source AI/agent-related projects.
- Familiarity with vector databases, embeddings, and retrieval-augmented generation (RAG).
