Lead/Principal AI Engineer

Role Overview

Partex.AI is looking for a Lead / Principal AI Engineer to architect, build, and scale enterprise-grade AI/LLM products, with strong expertise in Agentic AI, RAG, LLM orchestration, cloud AI, and production AI systems.

Key Responsibilities

• Architect and develop enterprise LLM/AI solutions using AWS Bedrock, Azure OpenAI, or similar platforms.
• Design and implement Agentic AI and multi-agent systems using LangGraph, LangChain, or equivalent frameworks.
• Build scalable RAG architectures, embedding pipelines, hybrid search, grounding, and tool-calling systems.
• Transform AI prototypes into secure, scalable, high-availability production systems.
• Establish LLM evaluation, monitoring, observability, governance, and safety frameworks.
• Drive AI engineering best practices and AI-assisted software development.
• Mentor engineers and collaborate with Product, Data Science, and Engineering teams.
• Lead technical architecture and execution of strategic AI initiatives.

Desired Candidate Experience

• 8+ years in Software Engineering, AI/ML Engineering, or Technical Architecture.
• Strong hands-on experience building and deploying LLM/Generative AI solutions in production.
• Expert-level Python, APIs, microservices, system architecture, and production engineering.
• Strong experience with Agentic AI, multi-agent orchestration, RAG, vector databases, and LLM evaluation.
• Experience with AWS/Azure, enterprise data integration, and scalable AI infrastructure.
• Proven experience taking AI solutions from POC to production at scale.
• Experience mentoring engineers and leading cross-functional technical initiatives.
• Experience in Classical ML.

Good to Have

• Pinecone, Qdrant, Milvus, Knowledge Graphs, GraphRAG
• Multimodal AI, fine-tuning/PEFT, Kubernetes, GPU infrastructure
• LangSmith, Arize Phoenix, LLM observability and governance
• Open-source contributions, patents, or AI research/publications

Ideal Profile: A hands-on AI technical leader who can architect, build, deploy, and scale production-grade LLM and Agentic AI systems.