Senior Gen AI Scientist - Production-Grade LLM Systems

Robotics Technologies LLC; Houston (TX); On-site; USD 96,000 - 110,000; Full time

Job summary

Robotics Technologies LLC in Houston, TX is seeking a Senior Data Scientist + Gen AI to build production-grade Gen AI systems with a focus on prompt engineering, evaluation, and tool orchestration.

The role requires strong Python production experience, expertise in LLMs, AWS Bedrock, and workflow management (Airflow). You will work on security, RBAC, and observability, delivering measurable quality lift.

Qualifications

• Strong Python expertise with real production experience.
• Experience building Gen AI systems and large language model applications.
• Familiarity with AWS Bedrock and workflow orchestration (Airflow).
• Ability to design prompts, prompts policy, and tool integration.

Responsibilities

• Build production-grade Generative AI systems with emphasis on prompt engineering.
• Set up evaluation and observability: ground truth, confusion metrics, hallucination rate.
• Use LLM-as-judge with human review to ensure faithfulness and grounding.
• Design context management and agentic workflows for multi-step reasoning.
• Orchestrate tools and measure agent success rate; integrate AWS Bedrock and Airflow.
• Enforce security, privacy, RBAC and compliant data handling.

Skills

Large Language Models

AWS

Prompt Engineering

Python

Machine Learning

Gen AI

Confluence

Jira

Tools

Confluence

Jira

Job description

Robotics Technologies LLC in Houston, TX is seeking a Senior Data Scientist + Gen AI to build production-grade Gen AI systems with a focus on prompt engineering, evaluation, and tool orchestration.

The role requires strong Python production experience, expertise in LLMs, AWS Bedrock, and workflow management (Airflow). You will work on security, RBAC, and observability, delivering measurable quality lift.