Python AI Data Engineer

Client is building an internal AI data platform and is seeking a Lead AI Data Engineer to own and expand its flagship internal tool - Databot, an AI-powered data agent that enables business teams across marketing, finance, and operations to query and interact with company data through natural language.

This is a high-visibility, high-autonomy role. The engineer will be deeply embedded with internal stakeholders across the organization and must combine strong technical execution with a product mindset. The scope extends beyond maintenance: the successful candidate will build new internal data tools and, over time, contribute to productionizing these capabilities for external use.

Given the volume of internal collaboration required - all key stakeholders are US-based - this role requires US timezone availability. Night-shift coverage from India may be considered for exceptional candidates., 1. Databot Ownership & Expansion

• Maintain, stabilize, and enhance Databot - a Python-based agentic data query tool

• Extend Databot with new data sources and use cases as identified by business teams

• Collaborate with the original Databot developer (peer engineer) for knowledge transfer and architectural decisions

1. Internal Data Tool Development

• Engage directly with internal teams (marketing, finance, product, engineering) to identify unmet data needs

• Translate stakeholder requirements into well-scoped, production-grade internal tools

• Design data pipelines, semantic layers, and consumption interfaces appropriate to each use case

1. Productionization & Scalability

• Evaluate internal tools for potential external productionization

• Ensure tools meet deployment standards - containerized, Kubernetes-ready, monitored

1. Stakeholder Communication

• Run discovery sessions with internal business owners to understand data access and reporting needs

• Translate non-technical requirements into data product specifications

• Provide regular updates on tool roadmap and delivery status to engineering leadership, The platform operates on internal business metadata - cluster data, invoice data, marketing data, and external market data. No customer PII is involved. Data volume is in the triple-digit gigabyte range (~100-999 GB). The Databot agent currently surfaces this data to business teams via natural language queries.

• Python - primary development language; existing Databot codebase is Python

• Docker - containerization; Databot is deployed via Docker files

• Kubernetes - deployment target for all tools

• Shell scripting - utility scripts in the existing codebase

Data & Analytics (strong preference):

• BigQuery or equivalent cloud data warehouse

• Semantic layer concepts - understanding of how data gets modeled for consumption

• Experience working with dashboards, BI tools, or data reporting pipelines (tool-agnostic; mindset matters more than specific tool)

• Monitoring - instrumentation and observability for data pipelines and agents

AI & Agentic Systems (openness to learn is acceptable):

• MCP

• LLM-based agentic data consumption - experience with data agents or AI-powered query tools

• Google Cloud AI stack: Gemini, Vertex AI

• Familiarity with vector databases a plus (Client’s context), * Full-stack engineering capability with Python as the primary language

• Experience working directly with data - curating, wrangling, and building data-driven outputs

• Product mindset: ability to work from ambiguous stakeholder needs to a shipped tool

• Strong communication skills - this role is as much discovery and alignment as it is coding

• US timezone availability for internal collaboration

• Comfort operating as an independent contributor with minimal team structure

• Prior exposure to agentic AI systems or LLM-based data querying

Differentiators:

• Experience shipping internal tools that later became external products

• Background in data lake architecture or data federation across heterogeneous sources

• Startup or scale-up experience where scope and technology evolve rapidly