Senior NLP Engineer Needed for RAG Service Build

Pinecrest Systems

Contract · Remote · Flexible hours

About the role

Pinecrest Systems is modernizing its customer‑facing platforms to boost performance and reliability. As an NLP Engineer you will lead the redesign of the conversational analytics pipeline, ensuring low‑latency, high‑throughput processing for millions of daily interactions. This short‑term gig focuses on delivering a robust, scalable solution for the new "Sentinel Voice" module.

Key responsibilities

• Refactor the existing intent‑extraction service using spaCy 3.x and Ray for distributed inference.
• Implement real‑time monitoring dashboards in Grafana to track latency, error rates, and throughput.
• Migrate legacy Python 2 code to Python 3.11, adding type hints and unit tests with pytest.
• Integrate a caching layer with Redis to reduce duplicate request processing.
• Optimize REST endpoints for batch processing, achieving sub‑100 ms response times.
• Document the new architecture and hand‑off procedures for the operations team.

Must-have skills

• 5+ years of NLP engineering experience, including transformer fine‑tuning.
• Proficiency with Python, spaCy, PyTorch/TensorFlow, and Ray.
• Strong knowledge of REST API design and performance profiling.
• Experience deploying services on Kubernetes or Docker Swarm.
• Familiarity with monitoring tools such as Prometheus/Grafana.

Nice to have

• Background in low‑latency speech‑to‑text pipelines.
• Exposure to A/B testing frameworks for model rollout.