Python Developer RAG / GenAI Engineer

Bramkas Inc.
Dallas, United States of America
15 days ago

Role details

Contract type
Permanent contract
Employment type
Full-time (> 32 hours)
Working hours
Regular working hours
Languages
English
Experience level
Senior

Job location

Remote
Dallas, United States of America

Tech stack

API
Artificial Intelligence
Amazon Web Services (AWS)
Encodings
Document Retrieval
Python
Metadata
Meta-Data Management
Parsing
Data Streaming
Unstructured Data
Data Processing
Real Time Systems
Data Ingestion
Retrieval-Augmented Generation
Large Language Models
Multi-Agent Systems
Indexer
Backend
Software Coding

Job description

We are looking for a hands-on engineer who can build end-to-end GenAI pipelines - from document ingestion to retrieval and response generation.

You will work on modern AI architectures involving vector databases, embeddings, and real-time LLM integrations, helping deliver production-grade intelligent systems., * Build and maintain applications using Python for AI/GenAI use cases

  • Design and implement RAG-based architectures for document retrieval and response generation

  • Develop document ingestion pipelines:

  • Loading * Parsing * Chunking * Embedding * Storage

Work with vector databases for similarity search and indexing

Implement document citation / source attribution in LLM responses

Integrate with LLM providers (OpenAI, AWS Bedrock, etc.)

Develop real-time systems using Streaming APIs and Server-Sent Events (SSE)

Handle metadata management, indexing, and retrieval optimization

Work with agent-based systems and integration patterns (MCP or similar)

Collaborate with product, UI, and backend teams for full solution delivery

Requirements

  • Experience: 5 + Years Experience
  • Skills : GEN AI , RAG , Python

We are actively hiring for a Python Developer with strong experience in RAG (Retrieval Augmented Generation) and GenAI-based systems to build intelligent, scalable AI applications., * Strong hands-on experience in Python development

  • Proven experience building RAG (Retrieval Augmented Generation) systems

  • Experience with Vector Databases:

  • Embeddings, similarity search, indexing

Strong experience in:

  • Document parsing & extraction (PDF, structured/unstructured data)
  • Document ingestion pipelines

Experience with:

  • Streaming APIs and SSE (Server-Sent Events)
  • LLM integrations (OpenAI, Bedrock, etc.)

Understanding of:

  • MCP (Model Context Protocol) or similar agent frameworks

Strong knowledge of data handling, metadata, and retrieval optimization

Good to Have

  • Experience with LangChain / LangGraph or similar frameworks
  • Experience with chat-based or agent-based UI integrations
  • Exposure to real-time AI applications and conversational systems, * Strong problem-solving mindset with hands-on coding ability
  • Experience building production-grade AI systems (not just POCs)
  • Ability to work independently in a fast-paced environment
  • Passion for working with modern AI / GenAI technologies

Apply for this position