Senior Applied AI Engineer/AI Technical Lead/AI Architect

Sectech Solutions is seeking a highly experienced Senior Applied AI Engineer / AI Technical Lead / Architect to lead the design and development of enterprise-grade Generative AI solutions. The role involves hands-on engineering, solution architecture, and technical leadership, focusing on building scalable AI systems that solve complex real-world problems.

Responsibilities:

• Own the end-to-end technical design of applied AI solutions across multiple business domains
• Design scalable LLM-based architectures, including:
• Retrieval-Augmented Generation (RAG) pipelines
• Agent-based workflows and tool orchestration
• Human-in-the-loop checkpoints
• Define integration patterns between AI services and enterprise systems such as policy administration, claims, and CRM platforms
• Establish reference architectures for POC, pilot, and production deployments
• Build end-to-end AI prototypes and production systems in Python
• Implement and optimize:
• Prompt engineering strategies
• Retrieval pipelines and embeddings
• AI agents and tool integrations
• API services and model inference layers
• Evaluate and prototype emerging GenAI technologies including:
• GPT-4
• Claude
• Gemini
• Refactor and enhance existing AI codebases to meet enterprise standards
• Design scalable AI infrastructure using Azure OpenAI Service and Azure cloud services
• Define data flows, API contracts, and system integration patterns
• Establish reusable frameworks and AI development patterns to accelerate delivery across projects
• Implement observability, monitoring, and performance optimization across AI systems
• Provide technical direction to an offshore engineering team
• Conduct architecture reviews, code reviews, and deep-dive technical sessions
• Break complex AI architectures into clear development tasks
• Mentor engineers on best practices for applied AI, LLM systems, and production ML engineering
• Evaluate when to use GenAI vs traditional machine learning or rule-based approaches
• Make trade-off decisions across:
• Accuracy vs speed
• Cost vs capability
• Autonomy vs control
• Determinism vs flexibility
• Ensure solutions remain explainable, reliable, and enterprise-safe
• Implement guardrails for:
• PII handling
• Prompt safety
• Output validation
• Data security boundaries
• Partner with security, legal, and compliance teams to ensure responsible AI deployment
• Design fallback mechanisms and failure-handling strategies

Requirements:

• 7+ years in software engineering or AI/ML engineering roles
• 3+ years working with LLMs, Generative AI, or advanced NLP systems
• Strong Python development experience building production systems
• Deep understanding of Retrieval-Augmented Generation architectures
• Experience designing AI agents, tool orchestration, or multi-step AI workflows
• Experience with cloud-based AI infrastructure (Azure preferred)
• Familiarity with vector databases, semantic search, and embeddings
• Experience designing secure and scalable enterprise AI systems
• Strong architectural thinking and ability to lead technical decision-making
• Experience mentoring or leading engineering teams
• Experience in regulated industries such as insurance, financial services, or healthcare
• Hands-on experience with vector search systems and knowledge retrieval
• Familiarity with evaluation frameworks for LLM outputs and model performance
• Experience building reusable AI platforms or internal developer frameworks