LLM Application Engineer

Position:
LLM Application Engineer Conversational AI Analytics

Location:

Rockville, MD or Tysons Corner, VA (3 days onsite & 2 days remote per week)

Duration: 6‑month contract

• Conversation Analytics & Insight Generation:
  Design and implement analytics pipelines that extract meaningful patterns from large‑scale chat conversation data. Develop facet extraction approaches using LLMs to categorize conversations by request type, task performed, and topic discussed. Build dashboards and reporting artifacts that communicate usage trends, emerging topics, and user behavior to stakeholders. Identify and quantify shifts in conversation patterns over time to inform product roadmap and content strategy.
  
  Translate analytical findings into actionable recommendations for platform improvement.
• Clustering & Unsupervised Learning:
  Architect and optimize hierarchical clustering pipelines using density‑based algorithms (e.g., HDBSCAN) to group conversations by semantic similarity. Generate and manage text embeddings at scale using embedding models for downstream clustering and similarity tasks. Design multi‑level clustering strategies that produce both granular groupings and higher‑order category taxonomies. Evaluate cluster quality using persistence metrics, silhouette analysis, and domain‑informed validation. Experiment with clustering parameters, distance metrics, and dimensionality reduction techniques to improve grouping coherence.
• Data Engineering & Pipeline Development:
  Build and maintain data pipelines using Python for ingesting, transforming, and analyzing conversation datasets. Develop automated workflows using cloud‑native orchestration and compute services to run analytics at scale on scheduled cadences. Work with object storage, search engines, and relational databases to store and query analytical outputs. Implement caching, batching, and incremental processing strategies to handle large embedding and clustering workloads efficiently.
  
  Maintain reproducible analysis environments and version analytical artifacts (models, cluster outputs, embeddings).
• LLM‑Assisted Analysis:
  Design and refine LLM prompts for facet extraction, cluster labeling, and conversation summarization. Evaluate LLM output quality for analytical tasks and iterate on prompt strategies to improve accuracy. Leverage model infrastructure for embedding generation and LLM inference. Explore emerging techniques in LLM‑driven data analysis, topic modeling, and automated insight generation.
• Quality & Testing:
  Develop evaluation frameworks to measure clustering quality, facet extraction accuracy, and analytical pipeline correctness. Build automated regression tests to detect drift in clustering outputs or degradation in categorization quality. Validate analytical results against known baselines and domain expertise. Document methodologies, assumptions, and limitations of analytical approaches.
• Security & Compliance:
  Assist with adherence to technology policies and comply with all security controls. Implement secure coding practices, particularly in handling personally identified information (PII) and sensitive data. Participate in threat modeling and security discussions for API and infrastructure components. Understand and apply organizational security standards and best practices.

For applications and inquiries, contact: