Senior Agentic AI, Adaptive RAG engines Engineer

US Company is searching for a couple of Senior AI Engineers into a complex, enterprise-level project for building sophisticated Agentic Systems, Adaptive RAG engines, capable of autonomous research to solve complex, real-world problems. Interesting project with cutting edge technologies, distributed team, full-time, an official contract. Remote work, flexible schedule.

Brief project description:

• The product is SaaS, which allows multiple functions for sustainability & operational risk management. The project is dedicated for developing of AI Center of Excellence.

Key areas of responsibility:

• Platform Engineering: Build and enhance scalable, reusable AI services (e.g., "Adaptive RAG Engine," "Text-to-SQL Service," and "Agentic Runtime") that product teams can easily integrate.
• Technical Contribution: Collaborate with principal engineers and architects. Participate in code reviews, write robust tests, and help drive the adoption of engineering best practices (CI/CD for AI, evaluation).
• Agentic Innovation: Develop and implement multi-agent systems capable of complex reasoning, planning, tool use, and self-correction (using frameworks like LangGraph or PydanticAI or Databrics' Agent Brics).
• Data Engineering: Load datasets and knowledge sources from external systems. Shape and transform data to optimize it for Hybrid or Semantic Search, providing the best possible knowledge context to LLMs.
• Production Readiness: Help move prototypes to production with a focus on latency, cost optimization, and reliability. Implement robust evaluation pipelines (LLM-as-a-Judge) to measure quality and prevent regression.
• Collaboration & Enablement: Partner with product teams to implement their AI roadmaps. Translate business requirements into concrete technical implementations.

Required skills (at least one or more for each category):

• Professional Experience: At least 5 years of professional experience in software development or Data Science.
• Education: Bachelor's or Master's degree in Computer Science, Mathematics, Engineering, Physics, or a related natural science field.
• Python Expertise: At least 5 years of hands-on experience with Python, writing clean, maintainable, and production-ready code.
• Strong Software Engineering Foundation: distributed systems, API design (FastAPI), and cloud architecture.
• Data Engineering Expertise: Data Engineering and Big Data (DeltaLake, Databrics etc.) experience are a big plus.
• GenAI Engineering Experience: Hands-on experience building production RAG systems. Chunking strategies, hybrid search (dense + sparse), re-ranking, and context management.
• Agentic Workflow Experience: You have experience building systems where LLMs use tools, maintain state, and execute multi-step plans. You are familiar with the challenges of loops, recursion, and hallucination mitigation.

Tech Stack:

• Languages: Python, TypeScript
• AI Frameworks: LangChain/LangGraph, Pydantic AI, MosaicAI
• Models: Azure OpenAI (GPT-4o, o1), Open Source LLMs (Llama 3, Mistral)
• Infrastructure: Azure AI Search, Azure Container Apps, Delta Lake, Vector Databases like Databrics Vector Search.

Work conditions:

• Distributed team, remote work.
• Kanban or scrum approach, 5-6 team members / team.
• Full-time (40 hours per week).
• Official contract: salary, sick-leave days, holidays, vacations.

Hiring process:

• Step 1 - preliminary interview (main questions) - 20 mins
• Step 2 - internal tech interview (tech questions) - 40-50 mins
• Step 3 - tech interview with team leader and architect - 1 hour