Engineering AI/ML Large Language Models (LLM) SQL Machine Learning Python
We are building data analytics agents that leverage LLMs to help users extract insights from our data platform (Databricks). These agents must go beyond natural-language interfaces—they are expected to reason over data, generate correct queries, interpret results, and deliver actionable insights that business users can trust. This role is responsible for designing systems where LLMs interact safely and reliably with production data, under real-world constraints such as data scale, schema complexity, governance, and performance. Core Responsibilities - Build an agentic analytics platform using LLMs, including multi-step agents, tool orchestration, and reusable agent skills - Design context engineering and memory systems (session and long-term) to support complex, multi-turn analytics workflows - Enable safe, reliable access to Databricks data through validated SQL generation, semantic layers, and governance guardrails - Transform query results into accurate, explainable, decision-ready insights, not just tables or charts. - Implement automated evaluations and agent observability, including tracing, correctness checks, and failure detection
- 4+ years of professional experience in software engineering, applied ML, or AI engineering - Hands-on experience building LLM-powered or agentic systems in production: langchain, crewAI, agno, … - Strong proficiency in Python, asynchronous programming and backend system design. - Solid understanding of SQL, analytical queries, and data modeling - Experience designing reliable systems with validation, monitoring, and graceful failure handling: opentelemetry, grafana and prometheus stack, … - Strong intuition for LLM failure modes, correctness, and trust in production systems
- Competitive package - Hybrid working model - Macbook Pro provided for work - Bonus: 13th month salary - Weekly learning sessions and offsites - Close-knit small team culture
product companies experienced is a must have require?