Generative AI Engineer – Build Technology That Puts Millions Back to Work

Why This Role Matters

If you're an engineer who wants your work to touch millions of lives, this is your chance.

At Maayu, we're building Multi model AI Assistants that help millions of people find jobs, build skills, and navigate their careers. Your code won't just optimize metrics. It will unlock opportunities on a national scale.

You will build AI systems that guide real people toward real jobs, faster and more fairly than ever before.

If you're looking for
purpose, autonomy, and cutting-edge engineering

, this is the place.

About the Role

We are hiring a hands-on Generative AI Engineer with deep expertise in Retrieval-Augmented Generation (RAG), prompt engineering, and agentic AI. You'll design, build, and optimize intelligent agents using both open-source and proprietary LLMs (LLaMA, Mistral, Claude, GPT-4o, etc.).

This role is ideal for someone who loves building production-grade agents, experimenting with prompt strategies, and pushing the boundaries of what AI can do in real-world systems.

What You Will Build & Own

• Architect, design, and iterate on advanced prompt strategies for local and hosted LLMs.
• Build high-accuracy RAG pipelines using embeddings, retrievers, and context optimization.
• Create multi-step prompt chains and tool-calling workflows for dynamic, autonomous agents.
• Design, test, and deploy robust agent architectures using OpenAI tool-calling and agent protocols.
• Implement Guardrails, safety layers, and control flows to ensure predictable agent behavior.
• Debug, optimize, and maintain reliable agent codebases at scale.
• Use orchestration frameworks (OpenAI Operator, Responses API, A2A SDK) to manage agent lifecycle.
• Collaborate with research, product, and infra teams to deliver AI agents with sub-second latency and high reliability.

What We're Looking For (Must-Haves)

• 3–5 years in AI Engineering, Prompt Engineering, Applied ML, or related fields.
• Proven experience with open-source downloadable models AND hosted LLM APIs.
• Strong understanding of prompt design patterns, chaining strategies, error handling, and observability.
• Ability to build agents that are secure, auditable, self-correcting, and production-ready.
• Solid programming experience in Python, FastAPI, or similar frameworks.
• Experience with containerized deployments, CI/CD, and scalable microservices.
• Familiarity with RAG, vector stores, context compression, and retrieval optimizations.

Tech Stack You'll Work With

Languages & Frameworks: Python, FastAPI, LangChain, LlamaIndex

Vector DBs: Weaviate, Pinecone, Qdrant

Agent Stack: Responses API, OpenAI Operator, A2A SDK

Infra: Docker, GitHub Actions, GCP/AWS

Bonus Skills (Nice-to-Have)

• Building complex multi-agent systems with delegation, transfer learning, or persistent memory.
• Understanding of Model Context Protocols for multi-agent integrations.
• Experience deploying voicebots using Piepecat/Livekit or similar real-time frameworks.
• Familiarity with LoRA/QLoRA fine-tuning for domain-specific models.
• Expertise with scalable vector DB pipelines, compression strategies, or long context reasoning.

Why Top Engineers Choose Maayu

• Mission with massive impact: Your work directly improves employment outcomes for millions.
• Cutting-edge challenges: Multi-agent orchestration, real-time voice agents, RAG at scale.
• Build something new: We are creating AI assistants for the future workforce.
• Startup speed + real-world scale: Ship fast, iterate fast, impact fast.
• Ownership & autonomy: Engineering-driven culture where you influence architecture and product.

If you want to build meaningful AI that changes lives, not just dashboards — we would love to meet you.