Jobs at Blanc Labs

Build and ship full-stack features for a production AI agent platform, including Python backend services, APIs, Next.js interfaces, LLM agent capabilities, real-time voice and messaging integrations, data models, migrations, background jobs, observability, and reliability improvements. The role involves contributing to the roadmap, prototyping agent capabilities, and debugging issues across the application and live conversations.

Architect and deliver production-grade agentic AI platforms on Azure using Azure OpenAI, vector search, tool calling, and orchestration frameworks. Lead systems from MVP through productization, ensuring scalability, security, reliability, observability, and operational readiness. Define API and integration standards, deploy Azure infrastructure, establish monitoring and SLOs, evaluate emerging agent frameworks, and support incident management. Collaborate with DevOps, SRE, and distributed cross-functional teams to document architectures and enable reusable platform components.

Designs and maintains scalable Azure data pipelines, lakehouse architectures, governance frameworks, semantic models, ontologies, taxonomies, and Neo4j knowledge graphs. The role integrates RDF and OWL standards with enterprise analytics and AI/ML applications, ensuring data quality, lineage, security, and performance. It collaborates with architects, analysts, and business stakeholders to translate complex relationships into reliable data solutions and documented architectural designs.

Lead enterprise data architecture strategy across data lakes, warehouses, modern cloud platforms, and AI-enabled ecosystems. Design data models, ETL/ELT pipelines, MDM frameworks, governance standards, metadata and lineage practices, and scalable AWS, Databricks, and Microsoft Fabric solutions. Collaborate with data science and business teams on machine learning, GenAI, and agentic AI use cases. Provide technical leadership, mentor data engineers, troubleshoot complex platform issues, and drive performance and observability improvements.

Develop and deploy enterprise AI solutions using machine learning, NLP, generative AI, GPT models, and agentic systems. Identify automation opportunities, map business processes, build scalable data pipelines, create analytics dashboards, and deliver cloud-based solutions primarily on Azure. Improve model performance and translate business needs into practical AI strategies across procurement, inventory, and operations.

Lead the end-to-end development and lifecycle management of production machine learning models on Microsoft Azure. Responsibilities include data preparation, feature engineering, model training, deployment, API integration, MLOps pipelines, monitoring, retraining, and troubleshooting model drift. The role collaborates with data scientists, AI engineers, and data engineering teams while integrating Azure-native AI services and scalable cloud infrastructure.

Build and ship full-stack features for a production AI agent platform, including Python backend services, APIs, Next.js interfaces, LLM agent capabilities, streaming, tool calling, conversation state, and real-time voice and messaging integrations. Design database models and migrations, develop reliable background jobs, instrument services, troubleshoot end-to-end issues, and contribute ideas for new agent capabilities.

Own paid acquisition and conversion optimization for regulated financial-services lead-generation funnels. Manage Google and Meta campaigns, tracking, budgets, retargeting, landing pages, conversion copy, A/B testing, analytics, and end-to-end funnel performance. Ensure advertising complies with financial-services disclosure and platform restrictions, integrate an AI-powered feature into the conversion path, and operate within client-owned accounts and infrastructure while providing transparent handover of assets and data.

Design, build, and maintain scalable Azure-based data pipelines using Databricks, Spark, Python, and Azure Data Factory. Implement real-time CDC solutions, optimize ETL/ELT performance, ensure data quality across lakehouse and warehouse layers, and support analytics, reporting, and AI/ML use cases. Collaborate with architects, analysts, and cross-functional teams while documenting pipelines and promoting engineering best practices.

Lead the architecture and hands-on development of scalable cloud-native applications. Modernize monoliths into microservices, design APIs and event-driven integrations, implement AWS solutions, troubleshoot production systems, conduct code reviews, mentor engineers, and drive engineering, deployment, observability, and architectural best practices.

Design and evolve cloud-native enterprise architectures while remaining hands-on with coding. Modernize monolithic applications into distributed microservices, develop Java, PHP, and React applications, design APIs and asynchronous integrations, architect AWS solutions, troubleshoot production environments, improve observability, conduct code reviews, and mentor engineering teams. Collaborate with product, engineering, DevOps, and business stakeholders to drive scalable, resilient, and cost-efficient technical solutions.

Designs, builds, and deploys production AI features in Microsoft Azure. Responsibilities include backend services, APIs, LLM integrations through Azure OpenAI, prompt engineering, model evaluation, ML model deployment, CI/CD, monitoring, and production troubleshooting. The role collaborates with TPMs, Principal AI Engineers, and ML Engineers to deliver scalable, reliable AI-powered applications.