AI Architect

Job Description

Were looking for a seasoned Software Architect with deep expertise in cloud-native enterprise systems and Generative AI. You will define and deliver scalable secure and production-grade GenAI architectures including multi-agent RAG LLMOps and AgentOps systems and lead cross-functional teams to build and operate them. This role combines hands-on technical leadership systems thinking and strong stakeholder management.

Key responsibilities

Architecture & System Design

1. Design scalable modular and cloud-native architectures for GenAI applications(microservices event-driven serverless).
2. Define system boundaries data flows orchestration and integration patterns forLLMs vector DBs embedding services and tool integrations.
3. Produce architecture artifacts ( Layered Architecture Diagrams C4 Models DFDsClass Sequence ER & Use Case diagrams different types of blueprints APIcontracts design and trade-off decisions).
4. GenAI & Agentic Systems
5. Architect and deliver Retrieval-Augmented Generation (RAG) pipelines NaturalLanguage to SQL Flows fine-tuning strategies multi-modal capabilities and tool-augmented agents.
6. Design agent orchestration and multi-agent frameworks enabling planningreasoning and secure tool invocations implement and design Agent prototypes andCommunication Protocols.
7. Define prompt engineering standards memory models(episodic/semantic/procedural) and context management.

LLMOps & AgentOps

1. Define and implement model lifecycle pipelines: training fine-tuning validationdeployment rollback and monitoring.
2. Build AgentOps processes for agent lifecycle behavior tracking governance andperformance optimization.
3. Automate CI/CD for models agents and services (MLflow TFX BentoML custompipelines).

Integration Security & Compliance

1. Integrate GenAI services with enterprise systems (ERP CRM data lakes APIs) usingsecure scalable interfaces.
2. Ensure secure access controls data privacy encryption and compliance (GDPRHIPAA SOC2).
3. Define responsible AI practices: bias mitigation explainability audit trails andoutput governance.
4. GenAI security classify encrypt & sign data/models; enforce least-privilege withshort-lived creds and CI/CD security gates; telemetry drift/hallucination alerts kill-switch & runbooks.
5. Agentic AI security provable agent identity/attestation tool allowlist human gatefor high-risk actions; ephemeral scoped tokens sandboxed executionand replayable audit traces.

Observability Ops & Cost Optimization

1. Define telemetry tracing and logging for models and agents; monitor performancedrift hallucination rates and user feedback loops.
2. Build dashboards alerts and runbook guidance for operational health.
3. Design systems for cost efficiency (autoscaling spot instances serverlesschoices) and support FinOps practices.

Leadership Collaboration & Documentation

1. Lead cross-functional teams (product data science AI engineers platform)through architecture reviews workshops and technical decisioning.
2. Maintain architectural standards documentation playbooks and patternlibraries for GenAI systems.
3. Mentor engineers and evangelize best practices across the organization.

Required qualifications & experience

1. 10 years software engineering experience with 3 years in architecture or seniortechnical leadership roles (or equivalent).
2. Proven track record designing and delivering cloud-native production systems atenterprise scale.
3. Hands-on experience with GenAI/LLM systems RAG NL-SQLagentic frameworks or similar productionized AI applications.
4. Strong knowledge of system design patterns (microservices event-drivenCQRS hexagonal architecture) and Low Level Design Patterns.
5. Experience integrating ML/LLM services with enterprise data platforms and APIswhile meeting security/compliance requirements.
6. Solid engineering background in at least two languages (Python TypeScript GoJava C#) and familiarity with modern frameworks.

Technical skills & technologies (comprehensive)

1. Cloud & Infra: AWS / Azure / GCP; Kubernetes Docker serverless (Lambda Functions Cloud Run) GPU instances
2. GenAI & ML: Hugging Face Transformers OpenAI APIs LangChain LlamaIndex Semantic Kernel Haystack
3. Vector Stores: FAISS Pinecone Weaviate Chroma PostgrespgVector and other cloud vector stores
4. LLMOps / MLOps: Custom Development of Ops Pipelines MLflow TFX BentoML Kubeflow
5. Data & Integration: Kafka Spark Airflow Flink ETL/ELT concepts data lakes API gateways (Apigee etc)
6. DevOps & IaC: Terraform Pulumi CloudFormation GitHub Actions Jenkins
7. Observability & Security: Prometheus Grafana stack OpenTelemetry Jaeger ELK Datadog; Vault
8. IAM LDAP/OAuth2/OIDC/SAML Connect Snyk SonarQube SAST/SCA in pipelines OWASPs CWEs CVEs.
9. Databases & Storage: Relational (RDS/Cloud SQL) NoSQL (Mongo DynamoDB Cosmos DB) Redis S3/Blob/GCS ORM/ODM frameworks.
10. Agent frameworks / tools: Understanding of Basics of Agents required Langgraph Autogen AutoGPT AgentVerse MetaGPT CrewAI etc.
11. Performance & scalability: SSR/ISR caching strategies (CDN edge) lazy loading bundle optimization performance budgets.
12. Realtime & asyncRealtime & async: WebSockets SSE message brokers (Kafka RabbitMQ) background workers. Frontend frameworks: React () Angular Vue; component libraries and state (Redux/RTK Context Pinia Zustand)
13. Styling & UI tooling: Component Libraries Accessibility best practices Responsive UI
14. Frontend build & tooling: Vite Webpack Storybook UI Frameworks.
15. Backend frameworks: FastAPI serverless functions (AWS Lambda Cloud Functions)
16. API design & integration: REST gRPC OpenAPI/Swagger API versioning and contract testing GraphQL(Optional)
17. UX & product mindset: Design-system familiarity usability accessibility and working with designers

Behavioral & leadership skills

1. Strategic thinking with the ability to align architecture to product and businessgoals.
2. Excellent communicator: simplify complex technical concepts for technical andnon-technical stakeholders.
3. Strong mentorship skills able to raise team capability in GenAI architectureand engineering.
4. Pragmatic decision-maker with a bias for measurable outcomes and trade-offanalysis.
5. High attention to detail ownership and accountability for reliability securityand cost.

Nice-to-have

1. Experience operating LLMs in regulated industries (pharma).
2. Familiarity with prompt auditing hallucination detection and automated qualitychecks.
3. Background in knowledge engineering semantic search or knowledge graphs.
4. Academic background in CS ML or equivalent applied experience.
5. Mobile & cross-platform (optional): React Native Flutter basics for mobileintegration
6. Deliverables & success metrics (examples)
7. Production-ready GenAI architecture and deployment runbook.
8. Deployed RAG/agent pipeline with observable SLOs and monitoring dashboards.
9. Reduced model hallucination/incidents and measurable improvement inretrieval quality.
10. Architecture decision records (ADRs) standards library and cross-teamonboarding materials.
11. Cost targets achieved through optimized infra and autoscaling policies.

Required Experience:

Staff IC