Gen AI Architect

Hi,

Hope you are doing well.

Please find the below JD.

Job Title: Technical Lead - Gen AI Architect

Location: Jersey City, New Jersey (Hybrid)

Type of Hire: Full Time

Experience

• 10+ years in ML/Engineering
• Preference from Finance industry
• At least 5 years in architecture roles.
• Proven experience delivering production-grade solutions on Azure.
• Hands-on ownership of end-to-end application lifecycle—from design to deployment.

Responsibilities

• Lead architecture and development of enterprise web applications with integrated Generative AI.
• Define scalable, secure architectural patterns and implementation standards.
• Work closely with product, AI/ML, DevOps, security, and network teams to align business and technical goals.
• Drive full-stack development best practices across backend, frontend, and infrastructure.
• Architect and integrate LLMs, embeddings, RAG pipelines, and vector databases into production systems.
• Ensure production readiness—security, networking, monitoring, performance, and compliance.

Mandatory Technical Skills

Cloud Architecture (Azure)

• Deep experience designing cloud-native, microservices and event-driven architectures.
• Expertise with Azure App Services, AKS, Functions, API Management, Event Grid, Service Bus, Storage, and Key Vault.
• Strong understanding of subscription design, resource hierarchy, and environment isolation.

Networking & Security

• Hands-on experience with:
• VNETs, subnets, private endpoints, service endpoints.
• NSGs, ASGs, routing, firewalls, and VPN/ExpressRoute connectivity
• Whitelisting, IP restrictions, certificates, TLS, and enterprise-grade authentication flows.
• Experience implementing Zero Trust, RBAC, managed identities, and secure secrets handling.

Performance & Scalability

• Expertise in caching (Redis/CDN), async processing (RabbitMQ/Kafka), load balancing, auto-scaling, and performance tuning.

GenAI Integration

• Hands-on experience with Azure OpenAI, RAG patterns, embeddings, prompt engineering, vector search (Azure AI Search, PostgreSQL extensions).
• Experience orchestrating LLM pipelines in real-world production environments.

Backend Engineering

• Strong REST API design (versioning, throttling, API gateways).
• Expert in PostgreSQL/MongoDB, data modelling, query optimization.
• Experience with OAuth2, SSO, and secure coding aligned to GDPR/SOC2.