AI/ML Software Engineer

• Design and implement AI-powered systems including chatbots, RAG pipelines, and multi-agent workflows.
• Evaluate and select appropriate approaches (LLM-based vs non-LLM methods) based on performance, cost, and accuracy requirements.
• Contribute to system architecture decisions for data processing, retrieval strategies, and service integration.
• Develop scalable AI applications that integrate with enterprise systems and workflows.

Retrieval, Knowledge Systems & NLP:

• Build and enhance hybrid retrieval systems. (vector search, keyword search, and graph-based retrieval)
• Develop and maintain RAG pipelines and knowledge management systems.
• Implement graph-based knowledge representations. (e.g., case-law and statute relationships)
• Improve embedding models, reranking systems, and retrieval accuracy.
• Support document ingestion, indexing, and structured knowledge extraction.

AI Application Development:

• Build and maintain internal and external chatbot systems.
• Develop RPA (Robotic Process Automation) tools powered by LLMs and data pipelines.
• Implement translation, transcription, redaction, and document analysis systems.
• Design document generation and form automation pipelines.

Evaluation, Testing & Quality Assurance:

• Design and implement evaluation frameworks for AI/ML systems.
• Develop unit, integration, and system-level tests for AI workflows.
• Create synthetic datasets for benchmarking and model evaluation.
• Monitor and improve system performance including latency, accuracy, and cost efficiency.
• Validate AI outputs and implement hallucination mitigation strategies.

Deployment & Operations:

• Deploy AI/ML systems in hybrid cloud and containerized environments. (Docker-based)
• Optimize applications for constrained compute environments, including limited GPU availability.
• Support CI/CD pipelines and production release workflows.
• Ensure reliability, scalability, and maintainability of deployed systems.

Documentation & Collaboration:

• Document system designs, workflows, APIs, and technical decisions.
• Collaborate with cross-functional teams to define agent workflows and system requirements.
• Stay current with advancements in AI/ML and apply relevant techniques to production systems.

1. Strong proficiency in Python for backend and data system development.
2. Experience with SQL and relational databases. (e.g., PostgreSQL)
3. Hands-on experience integrating LLMs. (API-based or local deployment)
4. Experience with Docker and deploying containerized applications.
5. Strong understanding of data structures, algorithms, and clean coding principles.
6. Experience building or supporting production backend systems, APIs, and data pipelines.

Preferred Skills:

1. Experience with RAG systems, embeddings, vector databases, and reranking models.
2. Knowledge of graph databases. (Neo4j, Apache AGE, or similar)
3. Experience designing multi-agent or task-oriented AI systems.
4. Familiarity with fine-tuning embedding models or small language models.
5. Experience contributing to open-source software projects.
6. Understanding of hybrid cloud environments and distributed systems.
7. Familiarity with NLP techniques beyond LLMs. (classical NLP, structured extraction)
8. Experience with async processing, queues, and threading in backend systems.
9. Exposure to React or the Microsoft Teams Toolkit. (for chatbot UIs)