Job Description

Onsite/ Hybrid/ Remote: Onsite 4 days a week <\/span>
<\/div>

Duration: 6 months <\/span>
<\/div>

Work Authorization: <\/b><\/span> GC, USC, All valid EADs except H1B, OPT, CPT
<\/div>

Must Have: <\/b>
<\/p>

• 4–6+ years of data science or machine learning experience
  <\/li>
• NLP classification for customer messages or call transcripts
  <\/li>
• Intent, topic, sentiment, and multi -label classification
  <\/li>
• Confidence scoring and model evaluation
  <\/li>
• Text cleaning, deduplication, speaker handling, and PII -safe processing
  <\/li>
• Trend and anomaly detection
  <\/li>
• Python, PySpark, SQL, and pandas
  <\/li>
• Labeled dataset design and annotation workflows
  <\/li>
• Precision, recall, confusion matrix, and drift monitoring
  <\/li><\/ul>

  Responsibilities: <\/b>
  <\/p>

  • Build and deploy NLP classification models for customer communications.
    <\/li>
  • Develop intent, topic, sentiment, and multi -label taxonomies.
    <\/li>
  • Clean and prepare transcript and message data for modeling.
    <\/li>
  • Handle short -text cases, duplicate records, system messages, and speaker identification.
    <\/li>
  • Build trend and anomaly detection methods using baselines, seasonality, and channel mix.
    <\/li>
  • Design maintainable Python and PySpark data pipelines.
    <\/li>
  • Define sampling strategies and annotation guidelines for labeled datasets.
    <\/li>
  • Support reviewer adjudication and dataset quality validation.
    <\/li>
  • Track model precision, recall, confusion patterns, confidence scores, and drift.
    <\/li>
  • Implement secure processing for customer communications containing sensitive data.
    <\/li><\/ul>

    Qualifications: <\/b>
    <\/p>

    • 4–6+ years of relevant machine learning, NLP, or data science experience.
      <\/li>
    • Proven experience deploying NLP models into production.
      <\/li>
    • Strong experience with classification systems and text analytics.
      <\/li>
    • Advanced Python development and testing skills.
      <\/li>
    • Hands -on experience with PySpark, SQL, pandas, and scalable data pipelines.
      <\/li>
    • Experience creating and validating labeled datasets.
      <\/li>
    • Strong understanding of model evaluation, monitoring, and false -alert reduction.
      <\/li>
    • Experience working with governed or PII -bearing data.
      <\/li><\/ul>

      Nice to Have: <\/b>
      <\/p>

      • Databricks
        <\/li>
      • Unity Catalog
        <\/li>
      • Databricks Workflows
        <\/li>
      • MLflow
        <\/li>
      • Model and data versioning
        <\/li>
      • Retrieval and embedding models
        <\/li>
      • LLM -assisted classification with evaluation and guardrails
        <\/li>
      • Contact -center or customer -support analytics
        <\/li>
      • Property -management or real -estate data experience
        <\/li><\/ul>

        
        <\/div><\/span>
        

Job Tags

Similar Jobs