Senior AI Engineer

The Sr. AI Engineer will design, architect, and implement advanced AI systems leveraging multi-agent frameworks, RAG pipelines, and LLM orchestration layers. You’ll be responsible for building intelligent, scalable workflows that enable reasoning, contextual understanding, and autonomous task coordination across various enterprise use cases.

Key Responsibilities

• Architect and deploy multi-agent AI systems using frameworks like LangGraph, CrewAI, or custom orchestrators.
• Design and optimize Retrieval-Augmented Generation (RAG) pipelines for contextual reasoning and dynamic knowledge synthesis.
• Integrate vector databases and semantic search layers (e.g., Pinecone, Weaviate, FAISS) for efficient knowledge retrieval.
• Develop modular LLM pipelines combining tools, memory, and dynamic context switching.
• Implement Python-based AI microservices with robust APIs for reasoning, planning, and data processing.
• Conduct prompt engineering, evaluation, and adaptive tuning to improve model accuracy and reliability.
• Build autonomous data ingestion and learning loops to continuously improve AI system performance.
• Collaborate with cross-functional teams to align AI pipelines with product goals and business logic.
• Research and prototype new frameworks in agentic AI, self-correcting systems, and multi-modal reasoning.

Required Skills

• Minimum 5+ years of experience
• Strong expertise in LLMs, NLP, RAG architectures, and multi-agent orchestration.
• Proficiency in Python, LangChain, LangGraph, and OpenAI / Hugging Face APIs.
• Experience deploying AI pipelines in production environments (microservices or distributed systems).
• Hands-on with vector DBs, semantic embeddings, and knowledge graphs.
• Solid grasp of LLM evaluation, memory management, and context-aware reasoning.
• Experience integrating AI tools with backend systems (e.g., GitHub, Azure DevOps, RESTful APIs and FASTAPIs).
• Strong understanding of system design, data pipelines, and cloud-based AI architectures.

Nice to Have

• Familiarity with LangGraph, CrewAI, LlamaIndex, or Semantic Kernel.
• Experience building autonomous agents or self-improving task networks.
• Exposure to Azure OpenAI, Vertex AI, or Anthropic Claude API.
• Background in AI evaluation, reinforcement learning from human feedback (RLHF), or tool-augmented reasoning.
• Ability to mentor teams in prompt engineering, AI safety, and agentic framework design.