AI Engineer (LLM & Agentic Systems) — HIGH PRIORITY

Location: Onsite Type: Full-time

Experience: 4–7+ years (hands-on)

About the Role

We are looking for an AI Engineer to design, build, and deploy production-grade AI systems that power our marketplace operations. This role is highly hands-on and focused on real-world delivery, not research or experimentation.

You will work closely with backend, product, and engineering leadership to turn AI workflows into reliable, scalable services.

What Youll Do

• Build and deploy LLM-powered agents for internal operations and customer-facing workflows
• Design agentic workflows using LangChain and LangGraph
• Develop AI microservices using Python and FastAPI
• Implement RAG pipelines using vector databases
• Integrate LLMs (e.g., OpenAI) with business logic, APIs, and data sources
• Optimize prompts, memory, tools, and agent orchestration
• Ensure AI systems are production-ready (logging, monitoring, fallback handling)
• Collaborate closely with backend engineers on APIs and system design

Requirements

• Strong experience with Python (production systems)
• Hands-on experience with LangChain and LangGraph
• Experience building APIs with FastAPI
• Solid understanding of LLMs, prompt engineering, and agent architectures
• Experience with RAG, embeddings, and vector databases
• Ability to design reliable, maintainable AI workflows

Nice to Have (Bonus)

• Experience with OpenAI or similar providers
• Familiarity with Redis, queues, or async workers
• Cloud deployment experience (AWS/GCP/Azure)
• Experience with marketplaces, SaaS, or ops-heavy products
• Understanding of AI guardrails, safety, and cost optimization

What Success Looks Like

• AI agents running reliably in production
• Clear ownership of AI services (not experimental code)
• Measurable impact on operations and automation