Senior NLP Python Developer

We are supporting a critical backend re-engineering initiative for a platform preparing to scale to 40,000+ users by January. The system is currently built on a modular microservices architecture using Python (3.11), FastAPI, Flask, SQLAlchemy, and PostgreSQL, deployed via Docker and Kubernetes on AWS. The NLP stack includes LangChain and Weaviate for RAG pipelines.

The project involves a full database overhaul, NLP/RAG optimization, backend refactoring, and system hardening. You will work alongside a small internal team and report directly to the CTO.

Key Responsibilities

Database Overhaul

• Refactor and optimize the existing PostgreSQL schema for scalability and performance.
• Address incomplete data migration from Salesforce and improve data model consistency.
• Resolve issues with outdated dependencies and inconsistent versioning.

NLP/RAG Pipeline Optimization

• Completely refactor LangChain-based pipelines to improve speed and reduce LLM call costs. All the processing is sequential but needs to be parallelized. The other critical aspect is runtime decision-making on which model to call (based on capabilities and price).
• Optimize vector search and retrieval using Weaviate.
• Integrate additional external knowledge into the existing RAG pipelines to provide better context and data for model calls.
• Improve modularity and maintainability of the NLP codebase (currently using Poetry, pre-commit, Ruff).

Backend Refactoring

• Rebuild monolithic components into modular microservices.
• Align backend services with the new database and NLP architecture.
• Eliminate old/unused code and improve code quality and documentation across repositories.

Testing & Hardening

• Improve test coverage, especially for NLP and end-to-end workflows.
• Implement structured testing practices and CI/CD pipelines with comprehensive test stages.
• Harden the system for production use, including security, observability, and performance.

Required Skills & Experience

Backend & Full-Stack Development

• 5+ years of experience with Python, FastAPI, Flask, and SQLAlchemy.
• Experience with microservices architecture and containerized deployments (Docker, Kubernetes).
• Familiarity with infrastructure as code (Terraform) and CI/CD pipelines.

Database Expertise

• Deep experience with PostgreSQL: schema design, query optimization, and data migration.
• Ability to refactor legacy schemas and improve data integrity and performance.

NLP & RAG Systems

• Hands-on experience with LangChain and vector databases (Weaviate).
• Understanding of embedding models, LLM orchestration, and cost/performance trade-offs.

DevOps & Observability

• Experience with AWS services, including Secrets Manager and CloudFront.
• Familiarity with message queues (SQS, RabbitMQ), caching strategies, and CDN usage.
• Ability to implement centralized monitoring and error tracking (current system relies on Slack).

Security & Quality

• Knowledge of secure coding practices, secrets management, and vulnerability management.
• Experience improving code quality, documentation, and test coverage across multiple repositories.

Soft Skills

• Self-starter with strong problem-solving skills and ability to work independently.
• Excellent communication and collaboration in remote, fast-paced environments.