Rq Tech Hr

Job Overview:

Pay Range: $52/hr - $57/hr

Requirement/Must Have:

• 10+ years of experience in end-to-end RAG architecture ownership (ingestion → retrieval → generation) & LLM orchestration.
• 8+ years of strong hands-on Python backend/data engineering experience.
• 6+ years of experience with OpenAI APIs (embeddings + chat + tools).
• 6+ years of experience with MongoDB Atlas Vector Search (hands-on), Aurora MySQL + DocumentDB integration.
• 6+ years of experience with API + async pipelines + CI/CD.

Responsibilities:

• Own end-to-end architecture for ingestion, indexing, retrieval, and LLM orchestration (RAG).
• Lead implementation in Python (hands-on coding + design reviews + standards).
• Build and optimize data extraction pipelines from AWS Aurora MySQL and AWS DocumentDB.
• Design chunking/metadata strategy and indexing into MongoDB Atlas Vector Search.
• Integrate OpenAI for embeddings + generation.
• Implement MCP patterns for safe retrieval and extensible tooling.
• Establish production readiness: Observability, alerting, incident response runbooks.
• Provide technical leadership: Mentor engineers, set coding standards, conduct design/code reviews.
• Coordinate with product, data, and security stakeholders; manage technical roadmap.

Nice to Have:

• Hybrid retrieval (keyword + vector), reranking, evaluation frameworks.
• Document parsing/OCR, table extraction, knowledge graph/entity resolution.
• AWS deployment experience (ECS/EKS/Lambda), VPC networking, IAM best practices.

Skills:

• Strong experience with OpenAI APIs (embeddings + chat; tool/function calling patterns).
• Hands-on with MongoDB Atlas Vector Search: Index creation/tuning, schema design, metadata filtering.
• Strong integration experience with Aurora MySQL and DocumentDB.
• API/service development: FastAPI preferred; background jobs (Celery/RQ/SQS/Kafka).
• Engineering excellence: Docker, CI/CD, pytest, secure secrets, monitoring, performance tuning.

Qualification And Education:

• Prior experience as Lead/Tech Lead owning architecture and delivery of production systems.
• Proven experience shipping RAG/LLM applications in production.