Sanatjon B.

Key Skills

Software

AWS SageMaker

Top Subject Matter

LLM prompt workflows and output validation for AI-assisted product features

Structured extraction/classification using LLM prompts

Embeddings Domain Expertise

Top Data Types

Text

Top Task Types

Prompt + Response Writing (SFT)

Function Calling

Classification

Freelancer Overview

Senior Python Engineer at Ataraxis (AI-assisted backend with OpenAI API integration). Brings 8+ years of professional experience across complex professional workflows, research, and quality-focused execution. Core strengths include OpenAI API, Internal, and Proprietary Tooling. Education includes Bachelor of Computer Science, Brooklyn College (2026). AI-training focus includes data types such as Computer Code, Programming, and Text and labeling workflows including Prompt + Response Writing (SFT), Function Calling, and Classification.

Labeling Experience

Senior Python Engineer at Ataraxis (AI-assisted backend with OpenAI API integration)

Prompt + Response Writing (SFT)

Designed and implemented prompt workflows and validation guards to improve the quality of AI-generated outputs for end users. Developed mechanisms for checking and filtering invalid results, reducing error rates and increasing accuracy of AI-assisted features. Built prompt-related tooling as part of production AI-assisted backend services. • Defined prompt workflows and validation guardrails for AI outputs • Reduced invalid AI outputs by 25% via validation logic • Improved user-facing accuracy of AI-assisted features by incorporating output checks • Integrated prompt workflows into AI-assisted services for reliable production behavior

2024 - Present

Senior Python Engineer at Graphite (AI-driven data processing APIs)

Function Calling

Built AI-driven data processing APIs that performed structured extraction and classification over large datasets. Integrated AI platforms (OpenAI/Azure AI) to support prompts, embeddings, and retrieval workflows used for compliant and auditable outputs. Implemented automated testing for AI integrations to ensure stable structured outputs as models changed. • Used prompts, embeddings, and retrieval workflows to generate structured extraction/classification outputs • Ensured outputs were compliant and auditable • Implemented automated tests for AI integrations to maintain stability across model updates • Delivered end-to-end batch data pipelines feeding AI-driven API services

2022 - 2024

Software Engineer at Clay (AI-assisted features with embeddings and scoring)

Classification

Developed AI-assisted product workflows that used structured data, embeddings, and scoring/recommendation logic for job-matching and classification. Created structured outputs with validation to support internal decision-makers and downstream automation. Built and optimized the supporting data pipelines to enable low-latency processing for critical workflows. • Implemented job-matching and classification logic using structured outputs • Added validation to improve reliability of classification outputs • Used embeddings and scoring/recommendation logic for AI-assisted features • Optimized data pipelines to reduce latency and improve throughput

2019 - 2022

Education

Work History