We are seeking a highly skilled AI/ML Software Engineer with strong programming experience in Python to design, develop, and deploy intelligent software systems that leverage Artificial Intelligence and Machine Learning techniques.
This role involves working on cutting-edge solutions such as LLM agents, RAG systems, chatbots, document intelligence, and AI-powered automation tools.
Required Qualifications
Strong programming experience in Python
Solid understanding of:
Data structures & algorithms
Clean coding principles
Responsibilities:
AI/ML Development & System Design:
-
Design and develop AI/ML-powered applications for:
-
Document analysis, redaction, and generation
-
Chatbots and conversational AI
-
Knowledge retrieval using LLM agents
-
Translation, transcription, and data processing
Build and optimize RAG (Retrieval-Augmented Generation) systems
Design multi-agent AI systems and task-oriented workflows
Evaluate when to use LLM vs non-LLM approaches
Engineering & Architecture
-
Develop production-grade backend systems using Python
-
Build APIs, middleware, and scalable data pipelines
-
Work with service-oriented architecture and microservices
-
Integrate AI solutions into existing enterprise systems
Deployment & Operations
-
Deploy AI/ML solutions in hybrid cloud environments
-
Work with containerized applications (Docker)
-
Optimize applications for low-resource environments (limited GPU)
-
Maintain and monitor production AI systems
Required Experience:
1. SQL and relational database systems (e.g., PostgreSQL)
2. Fine-tuning small language models or embedding models
3. Contributing to or maintaining open-source software projects
4. Graph databases or graph extensions (e.g., Neo4j, Apache AGE)
5. Designing and implementing multi-agent or task-oriented AI systems
6. Embedding models, vector similarity, re-ranking, and graph retrieval techniques in RAG systems
7. Version control systems (e.g., Git), containerization technologies (e.g., Docker), and
service-oriented architectures
8. Collaborating with large language models (LLMs), including both API-based
integration and local deployment
9. Validating AI-generated outputs, mitigating hallucinations, and integrating AI tools
into production service pipelines