Digital Auxilius

Key Responsibilities

AI/ML System Development

• Design and implement AI agents and machine learning systems that power core product features.
• Develop conversational voice agents capable of real-time interaction using speech recognition, natural language understanding, and dialogue orchestration.
• Build LLM-powered systems for tasks such as document analysis, structured data extraction, contextual question answering, and automated decision support.
• Implement retrieval-augmented generation (RAG) pipelines combining vector databases and knowledge sources.
• Design multi-agent architectures that coordinate tools, APIs, and data sources to perform complex tasks.
• Develop prompt strategies, agent logic, and model workflows that ensure reliable, deterministic system behavior.

AI Infrastructure & System Architecture

• Architect scalable backend services that expose AI capabilities through APIs and microservices.
• Design modular AI pipelines that support multiple product features and services.
• Optimize inference pipelines for latency, throughput, reliability, and cost efficiency.
• Build systems capable of real-time and batch AI processing.

Data Engineering for AI

• Design and maintain data ingestion pipelines used for model training, evaluation, and inference workflows.
• Process, clean, and transform structured and unstructured datasets used by AI systems.
• Build automated pipelines that update embeddings, knowledge bases, and feature stores.
• Integrate internal and external data sources into AI workflows.

API Integration & Workflow Automation

• Build and maintain integrations between internal databases, CRM systems, and third-party AI platforms using REST APIs.
• Develop Python scripts and backend services that automate operational workflows such as data entry, reporting, and system synchronization.
• Implement AI-powered automation systems that reduce manual operational overhead.

Vector Search & Knowledge Systems

• Implement vector search infrastructure using tools such as Pinecone, Weaviate, FAISS, or similar systems.
• Design knowledge retrieval systems for RAG pipelines and agent workflows.
• Manage embedding pipelines and document indexing systems.

Quality Assurance & AI System Evaluation

• Evaluate AI system outputs, conversations, and model behavior to identify inaccuracies, hallucinations, or workflow failures.
• Analyze failure modes and continuously improve prompts, agent logic, and orchestration pipelines.
• Design evaluation frameworks and metrics to measure system performance and reliability.
• Conduct structured testing of conversational agents and automated workflows.

MLOps & Model Lifecycle Management

• Implement model versioning, experiment tracking, and reproducibility workflows.
• Develop CI/CD pipelines for deploying machine learning systems.
• Monitor deployed models for drift, performance degradation, and operational reliability.
• Maintain scalable infrastructure for model training, inference, and updates.

Production Deployment Support

• Collaborate with engineering and integration teams to deploy AI systems into production environments.
• Ensure deployed systems meet operational reliability, service standards, and regulatory requirements.
• Implement monitoring, logging, and observability tools to track system behavior and diagnose issues.

Security, Governance & Reliability

• Implement secure handling of sensitive data and AI inputs.
• Manage API credentials, access control, and system authentication for AI services.
• Ensure AI systems follow privacy and compliance requirements.
• Build safeguards to prevent misuse or unintended outputs from AI systems.

Product Collaboration & Rapid Prototyping

• Translate product requirements into scalable AI system architectures.
• Rapidly prototype new AI features and experimental capabilities.
• Work closely with product, engineering, and integration teams to deliver AI functionality across the platform.

Required Qualifications

• Bachelor's or master's degree in computer science, Artificial Intelligence, Machine Learning, or related field.
• 3+ years of building ML/AI systems in production environments.
• Strong Python programming skills with experience building backend services and automation scripts.
• Strong experience with large language models and NLP systems.
• Experience with prompt engineering, fine-tuning, RAG pipelines, and structured data extraction from unstructured sources.
• Experience building AI-powered APIs and integrating external AI platforms.
• Experience performing quality assurance and performance evaluation for AI-driven systems.

Technical Skills

• Machine learning frameworks such as PyTorch, HuggingFace Transformers, or similar.
• Conversational AI and agent orchestration frameworks such as LangChain or similar.
• Vector databases and embedding systems.
• REST API development and system integrations.
• Data processing and pipeline development using Python.
• Experiment tracking and ML lifecycle management tools.

Preferred Qualifications

• Experience building conversational voice agents or real-time AI interaction systems.
• Experience implementing vector search infrastructure or large-scale RAG pipelines.
• Experience with MLOps tooling such as MLflow, Weights & Biases, Kubeflow, or similar systems.
• Experience deploying AI services using containerization and cloud infrastructure (Docker, Kubernetes, AWS, GCP, or Azure).
• Familiarity with low-code or automation platforms such as n8n.