Senior Engineer (Agentic + Data/ML)

About This Role

Join a core engineering team to build agentic retrieval workflows, data pipelines, and ML/LLM-driven scoring systems for a leading U.S. video-content provider, enhancing engineering productivity and code quality across a large-scale infrastructure.

Responsibilities

• Improve CES with PR-level scoring, historical context, automated score correction, and training data preparation from feedback
• Ingest and track PRs, link to commits/branches, and monitor merges to main, including robust backfills
• Ensure orchestration and reliability through Dagster migration, retries, scheduling, monitoring, and data quality alerts
• Optimize LLM/prompt performance using DSPy-based tuning, evaluation set creation, feedback-driven corrections, and cost/quality tradeoffs
• Manage metadata and classification, including role/work-type classification, epic linking improvements, filters, and explorer features

Requirements

• Strong Python expertise
• Familiarity with modern data/ML tooling
• Proven delivery of production-grade orchestration systems on AWS
• Practical experience with prompt/LLM optimization (DSPy preferred)
• Comfortable working with Git/PR metadata, code diffs, backfills, and performance-critical data pipelines

Qualifications

• 5-10+ years as a software/data/ML engineer

Nice to Have

• Experience with code-scoring/effort or quality metrics
• SonarQube integration
• Graph-ish linking across artifacts (Jira/PR/commit/branch) for epic/work-type classification
• Experience tuning performance/cost for LLM calls (OSS LLM evals, batching, caching)
• Observability for pipelines (metrics/traces/logs) and data quality alerting

Skills

* Required skills