AI Architect

10+ years of software engineering experience with expertise in distributed systems and cloud-native applications.

3+ years designing, leading, or architecting AI/ML/Agentic platforms and large-scale AI initiatives.

Proven experience delivering production AI systems in enterprise SaaS environments.

Bachelor's or Master's degree in Computer Science, Engineering, Mathematics, or a related technical field.

Hands-on experience deploying and operating AI workloads on AWS or GCP at production scale.

Experience with cloud-native architectures, container platforms, serverless computing, and managed AI services.

Strong understanding of cloud security, identity management, secrets management, and least-privilege access controls.

Experience building scalable, secure, and highly available enterprise platforms.

Deep expertise in Agentic AI, RAG architectures, LLM orchestration, and prompt engineering.

Experience with multi-agent systems, tool calling, memory management, and workflow orchestration.

Strong understanding of embeddings, vector search, hybrid retrieval, reranking, and grounding techniques.

Experience designing query orchestration systems that leverage LLMs to interact with enterprise data.

Knowledge of model optimization, evaluation frameworks, and inference performance tuning.

Experience implementing AI governance, observability, quality evaluation, guardrails, and security controls for enterprise AI systems.

Experience with prompt registries, versioning systems, governance workflows, and environment-based promotions.

Experience with experimentation, evaluation, benchmarking, regression testing, and production monitoring.

Familiarity with model routing, tenant-specific AI configurations, and prompt performance optimization.

Python (Primary): Experience building production AI services, orchestration layers, APIs, agent runtimes, and data pipelines.

Java / Spring Boot: Experience integrating AI capabilities into enterprise applications and distributed systems.

Strong SQL and PostgreSQL expertise.

Experience designing event-driven and service-oriented architectures.

Experience with one or more of the following technologies:

Agentic AI & Orchestration: Strands, CrewAI, LangGraph, LangChain, LlamaIndex, OpenAI Agents SDK

Cloud & Platform: Amazon Bedrock, Vertex AI, Kubernetes, Docker, Terraform, Kafka

LLMOps & Observability: MLflow, Weights & Biases, OpenTelemetry, Prometheus, Grafana

Vector Search: pgvector, OpenSearch, Pinecone, Weaviate

Infrastructure-as-Code proficiency using Terraform, CDK, or similar technologies.

Experience deploying and operating AI workloads using Docker and Kubernetes.

Strong understanding of observability, distributed tracing, metrics, monitoring, and reliability engineering.

Experience implementing secure authentication, authorization, secrets management, auditability, and data protection controls for AI systems.

Experience with B2B SaaS multi-tenant architectures and per-customer AI customization at scale.

Background in partner ecosystem management, CRM/PRM platforms, or workflow automation platforms.

Contributions to open-source AI projects, agent frameworks, or published research.

Familiarity with multimodal AI, document intelligence, or knowledge extraction systems.

Experience with federated or on-premise AI deployments for enterprise customers.

Prior experience scaling AI platforms from 0 to 1 in a high-growth environment.