Senior Data Scientist + Gen AI

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

US Citizen, Green Card, H-1B, OPT-EAD, CPT, Other

• Job Title: Senior Data Scientist + Gen AI
• Location: Houston, TX
• Duration: 6 Months
• Bill Rate: $73/hour (C2C)
• Job Type: W-2, 1099, C2C
• Client: To Be Discussed Later
• Work Authorization: US Citizen, Green Card, OPT-EAD, CPT, H-1B, H4-EAD, Other

Build production-grade Generative AI systems with emphasis on:

• Prompt engineering (system prompts, tool prompts, function calling, versioning with evaluations)
• Evaluation & observability , including:
• Ground truth setup
• Confusion metrics
• Hallucination rate measurement
• LLM-as-judge with human review
• Context management
• Faithfulness & grounding validation
• Agentic workflows
• Multi-step reasoning
• Tool orchestration
• Agent success rate measurement
• AWS Bedrock
• Workflow orchestration
• Airflow
• Security & privacy
• RBAC
• Strong Python expertise with real production experience

Success Criteria:

• Measurable quality lift (accuracy, faithfulness, confusion metrics)
• Reduced hallucinations

Skills:

Large Language Models, AWS, Prompt Engineering, Python, Machine Learning, Gen AI, Confluence, Jira

We are an equal opportunity employer. All aspects of employment including the decision to hire, promote, discipline, or discharge, will be based on merit, competence, performance, and business needs. We do not discriminate on the basis of race, color, religion, marital status, age, national origin, ancestry, physical or mental disability, medical condition, pregnancy, genetic information, gender, sexual orientation, gender identity or expression, national origin, citizenship/ immigration status, veteran status, or any other status protected under federal, state, or local law.