Technical Lead – AI Engineering

Employment Type: Full-Time Experience: 8-10 Years Position Level: Technical Lead / Lead AI Platform Engineer About CogNet Drive CogNet Drive is an AI-powered intelligent document processing and workflow automation platform being developed by CogNet HR Solutions. The platform is designed to transform how organizations process, extract, validate, reconcile, analyze, and manage complex business documents. By combining Large Language Models (LLMs), Optical Character Recognition (OCR), agentic AI workflows, intelligent validation, and enterprise integrations, CogNet Drive aims to automate document-intensive business processes while delivering high accuracy, scalability, security, and operational efficiency. Our initial focus includes payroll and HR documents, employee benefits, insurance underwriting submissions, claims and loss-run reports, financial records, and other structured and unstructured business documents. We are looking for an experienced, hands-on Technical Lead - AI Engineering who can architect, develop, and lead the engineering efforts required to transform CogNet Drive into a scalable, secure, enterprise-grade SaaS product.

Role Overview The Technical Lead will be responsible for the overall technical architecture, engineering strategy, and delivery of CogNet Drive. This role requires a strong combination of software engineering expertise, cloud-native architecture, AI/LLM application development, and technical leadership. The ideal candidate must be capable of independently designing complex systems, solving challenging engineering problems, writing production-quality code, mentoring developers, and making critical architectural decisions. This is not a purely managerial position. We expect the Technical Lead to remain actively involved in architecture, coding, debugging, performance optimization, and production deployments. The candidate will work closely with product leadership, AI developers, backend engineers, frontend developers, and domain specialists to deliver a reliable, commercially viable AI platform. Key Responsibilities 1. Technical Architecture & Platform Engineering Own the end-to-end technical architecture of CogNet Drive, covering frontend, backend, AI processing, databases, integrations, and cloud infrastructure. Design scalable, modular, cloud-native applications using microservices, APIs, asynchronous processing, and event-driven architecture. Define architectural standards, coding guidelines, design patterns, and engineering best practices. Design a secure multi-tenant SaaS architecture supporting multiple enterprise customers. Architect reliable document ingestion, processing, validation, reconciliation, and output-generation workflows. Build systems capable of handling concurrent users, high document volumes, and computationally intensive AI workloads. Evaluate emerging technologies and recommend appropriate frameworks, infrastructure, and engineering approaches. Ensure the platform remains extensible, maintainable, and cost-efficient as product capabilities expand. 2. AI & LLM Engineering Lead the technical development and integration of AI-powered document processing capabilities. Architect LLM-based applications using Anthropic Claude, OpenAI, Amazon Bedrock, and other suitable models. Design and implement multi-agent workflows for document extraction, analysis, reconciliation, and validation. Establish structured-output mechanisms using JSON Schema, Pydantic, and deterministic validation. Develop model-independent AI integration layers that support switching between LLM providers. Implement prompt management, versioning, evaluation, and regression-testing frameworks. Design confidence scoring, exception handling, and human-in-the-loop review workflows. Optimize model performance, token consumption, latency, and processing costs. Evaluate retrieval-augmented generation (RAG), tool calling, agent orchestration, and other AI techniques where appropriate. Ensure AI-generated outputs are accurate, traceable, reproducible, and suitable for enterprise workflows. 3. Intelligent Document Processing & OCR Architect document-processing pipelines supporting PDF, Excel, scanned images, and other business document formats. Lead integration and optimization of PaddleOCR PP-OCRv4 and associated document-processing technologies. Develop intelligent mechanisms to distinguish digitally generated documents from scanned documents and select the appropriate processing approach. Design document classification, layout analysis, table extraction, and structured-data extraction workflows. Ensure reliable processing of complex documents containing tables, multiple sections, inconsistent layouts, and handwritten or scanned content where supported. Build validation and reconciliation engines capable of identifying missing information, inconsistencies, and discrepancies across multiple documents. Implement document-level and field-level traceability, confidence scoring, and exception reporting. Optimize OCR performance using CPU/GPU resources while controlling infrastructure costs. 4. Backend Development & API Engineering Lead the development of backend services using Python, FastAPI, and related technologies. Design and implement secure REST APIs for document upload, processing, workflow execution, status tracking, and output retrieval. Architect asynchronous task processing using AWS SQS, Step Functions, and worker-based execution. Implement robust error handling, retry mechanisms, idempotency, and recovery procedures. Design database schemas and data-access layers using PostgreSQL, SQLAlchemy, and related technologies. Develop integrations with HRIS, payroll, benefits, insurance, CRM, and third-party enterprise systems. Ensure seamless integration between AI services, backend APIs, and frontend applications. Establish API versioning, authentication, authorization, rate limiting, and performance standards. 5. AWS Cloud Architecture & DevOps Design, deploy, and manage CogNet Drive's AWS infrastructure. Work with AWS services including EC2, ECS, S3, RDS, SQS, Step Functions, Lambda, CloudWatch, IAM, and related services. Architect GPU-enabled document-processing infrastructure with intelligent resource allocation and autoscaling. Implement queue-based workload management, dynamic worker provisioning, and efficient resource utilization. Design systems supporting continuous operations with appropriate availability and disaster-recovery mechanisms. Establish CI/CD pipelines using GitHub Actions or equivalent technologies. Implement containerization using Docker and appropriate orchestration services. Define infrastructure-as-code practices using Terraform or AWS CDK. Monitor application performance, processing throughput, infrastructure consumption, and cloud costs. Drive infrastructure optimization without compromising performance, security, or reliability. 6. Product Scalability, Reliability & Performance Design the platform to support an initial workload of approximately 1,000 documents per day and a target of 100 concurrent users, with the ability to scale further. Engineer processing workflows toward a target turnaround time of 1-5 minutes for supported document-processing scenarios. Establish performance benchmarks for OCR, LLM processing, document validation, and output generation. Identify and eliminate processing bottlenecks across AI services, APIs, databases, and infrastructure. Implement distributed processing, caching, asynchronous execution, and resource optimization where appropriate. Establish monitoring, logging, alerting, and observability standards. Design fault-tolerant systems with retries, dead-letter queues, recovery mechanisms, and failure isolation. Define service-level objectives for availability, throughput, processing accuracy, and response time. Ensure the platform can scale efficiently as customer adoption and document volumes increase. 7. Security, Compliance & Data Protection Architect enterprise-grade security across application, infrastructure, and AI processing layers. Implement authentication, authorization, role-based access control, and secure tenant isolation. Design encryption mechanisms for data at rest and in transit. Ensure secure handling of confidential payroll, HR, financial, insurance, and personally identifiable information. Implement comprehensive audit logging, document access tracking, and processing traceability. Apply secure coding practices and integrate vulnerability assessments into the development lifecycle. Work within applicable ISO 27001, SOC 2, HIPAA, and GDPR requirements based on product and customer needs. Establish appropriate data retention, deletion, backup, and recovery mechanisms. Implement controls to prevent unauthorized data access, cross-tenant exposure, and sensitive-information leakage through AI services. 8. Technical Leadership & Team Management Provide technical direction and mentorship to AI developers, backend engineers, frontend developers, and other engineering resources. Translate product requirements into technical designs, engineering tasks, and development milestones. Conduct architecture reviews, code reviews, and technical design discussions. Establish engineering standards covering code quality, documentation, testing, security, and deployment. Actively contribute production code, particularly for critical components and complex technical challenges. Guide developers in troubleshooting, performance optimization, and root-cause analysis. Coordinate development activities across a lean, cross-functional engineering team. Work closely with product stakeholders to prioritize technical deliverables and manage dependencies. Identify technical risks early and recommend practical solutions. Build a culture of accountability, technical excellence, continuous learning, and engineering ownership. 9. Quality Engineering & Product Delivery Establish automated testing strategies covering unit, integration, API, performance, security, and end-to-end testing. Develop evaluation frameworks for measuring document extraction accuracy and reconciliation quality. Implement automated regression testing for prompts, AI models, OCR components, and document-processing workflows. Establish release management, deployment approvals, and rollback procedures. Ensure proper technical documentation covering architecture, APIs, infrastructure, and operational procedures. Collaborate with QA and product teams to establish acceptance criteria and release readiness. Support customer pilots, production deployments, incident resolution, and ongoing platform improvements. Take ownership of technical deliverables from design through successful production operation.

Requirements Required

Technical Skills Programming & Backend Development Strong proficiency in Python, including asynchronous programming and production application development. Extensive experience with FastAPI, REST APIs, Pydantic, and backend service architecture. Strong understanding of object-oriented programming, design patterns, and distributed systems. Experience with SQL, PostgreSQL, database optimization, and ORM frameworks. Working knowledge of C# / ASP.NET Core is an advantage. AI, LLMs & Document Intelligence Hands-on experience building production applications using LLM APIs. Experience with Anthropic Claude, OpenAI, Amazon Bedrock, or comparable AI platforms. Knowledge of LangChain, LangGraph, agent orchestration, tool calling, and structured outputs. Experience developing document extraction, classification, validation, or AI automation solutions. Familiarity with OCR technologies such as PaddleOCR, Tesseract, or Amazon Textract. Understanding of prompt engineering, model evaluation, hallucination mitigation, and AI reliability. Cloud & Infrastructure Strong practical experience with AWS cloud architecture. Experience with Docker, containerized services, CI/CD, and cloud deployments. Understanding of S3, ECS, EC2, RDS, SQS, IAM, CloudWatch, and related AWS services. Experience designing scalable asynchronous processing architectures. Familiarity with GPU-based workloads and infrastructure cost optimization. Architecture & Security Strong understanding of microservices, distributed systems, and event-driven architecture. Experience designing scalable SaaS platforms or enterprise applications. Knowledge of authentication, authorization, RBAC, encryption, and secure API design. Understanding of multi-tenant application architecture and data isolation. Familiarity with observability, application monitoring, and production incident management. Qualifications & Experience Bachelor's or Master's degree in Computer Science, Information Technology, Engineering, or a related discipline. 8-10 years of professional software engineering experience. At least 3 years of experience in a senior engineering or technical leadership role. Demonstrated experience architecting and delivering production-grade enterprise applications. Strong hands-on Python backend development experience. Practical experience integrating LLMs or AI capabilities into real-world applications. Experience working with AWS cloud infrastructure and distributed processing systems. Proven ability to lead small engineering teams while remaining actively involved in development. Experience taking products from proof of concept through production deployment is strongly preferred. Preferred / Additional

Qualifications Experience related to building commercial SaaS products from the ground up. Experience with intelligent document processing, insurance technology, payroll, HR technology, or financial automation. Knowledge of document layout analysis, OCR optimization, and GPU-based inference. Experience with React, TypeScript, or modern frontend technologies. Familiarity with RAG, vector databases, and AI evaluation frameworks. Experience implementing enterprise-grade data governance and compliance controls. Exposure to MLOps, LLMOps, infrastructure-as-code, and automated cloud provisioning. AWS certifications or relevant cloud architecture certifications. Experience integrating with HRIS, payroll, insurance carrier, or financial systems. Key Performance Indicators The Technical Lead will be evaluated against the following outcomes: Platform Delivery Successful transformation of CogNet Drive from proof of concept into a production-ready SaaS platform. Timely completion of agreed product milestones and technical deliverables. Quality, maintainability, and extensibility of the platform architecture. AI Processing Accuracy Target document-processing accuracy of 98% or higher for defined, benchmarked workflows. Reduction in manual intervention and processing exceptions. Reliable extraction, reconciliation, and validation across supported document types. Performance & Scalability Achievement of agreed document-processing turnaround targets. Reliable support for planned document volumes and concurrent users. Efficient CPU/GPU utilization and controlled infrastructure costs. Security & Reliability Effective tenant isolation, access controls, and auditability. Production stability, monitoring, and incident response. Adherence to established security and engineering standards. Engineering Leadership Development productivity and code quality. Effective mentoring and technical guidance. Reduction in technical debt and recurring production defects. Successful coordination of engineering activities across the product team. What We Are Looking For We are looking for a builder, architect, and technical leader rather than someone focused exclusively on project coordination or people management. The ideal candidate is someone who: Enjoys solving difficult technical problems and building products from the ground up. Can independently translate business requirements into scalable technical solutions. Understands both traditional software engineering and modern AI application development. Has strong architectural judgment without losing touch with hands-on coding. Can work effectively in a lean engineering environment. Takes ownership of technical decisions, quality, security, and production outcomes. Is comfortable experimenting with emerging AI technologies while maintaining engineering discipline. Can balance innovation, delivery speed, reliability, and cost efficiency. Why Join CogNet? CogNet Drive represents an opportunity to build a next-generation AI-powered enterprise automation platform with applications across payroll, HR, insurance, finance, and other document-intensive industries. As the Technical Lead, you will have significant ownership of the product's technical direction and architecture, with the opportunity to build and guide the engineering team responsible for bringing the platform to market. You will work on practical AI engineering challenges involving LLMs, intelligent document processing, agentic workflows, cloud infrastructure, and enterprise-scale automation. This is an opportunity to lead the engineering of a real AI product-not simply integrate AI features into an existing application.