We are seeking a Senior AI Engineer with deep LLM expertise to design and implement
advanced multi-agent AI systems, RAG pipelines, and AI infrastructure as part of an
early engineering team.
Key Responsibilities
- Build multi-agent AI systems orchestrating complex workflows and intelligent automation
- Develop advanced RAG pipelines with hybrid search capabilities using vector and keyword-based retrieval
- Design prompt engineering frameworks ensuring consistent, high-quality outputsacross multiple LLMs such as Claude, GPT, and Qwen
- Create context management systems optimizing token usage and maintaining conversation coherence
- Fine-tune models specialized for domain-specific knowledge and terminology
- Implement vector search infrastructure leveraging OpenSearch for semantic similarity and knowledge retrieval
- Develop LLM evaluation frameworks with automated quality metrics and regression testing
- Work on orchestration with LangChain for autonomous decision-making and task delegation
- Implement advanced prompt engineering including chain-of-thought and tree-of-thought reasoning
- Optimize context windows for long-form content generation and multi-turn conversations
- Build hybrid retrieval systems combining dense and sparse search with intelligent ranking
- Fine-tune models using PEFT techniques for domain adaptation
- Implement cost optimization through model routing, caching, and token management
- Collaborate with AI and backend teams to integrate AI systems into production environments
- Establish engineering standards for AI platform development
Required Skills:
- 3-5+ years building production AI systems
- Production experience with Amazon Bedrock or similar managed LLM services
- Expert-level prompt engineering
- Context window and memory management for long conversations
- RAG development and vector search expertise using OpenSearch or similar databases
- Fine-tuning models such as Llama or Mis