Job description
Project Role : Technology Architect
Project Role Description : Design and deliver technology architecture for a platform, product, or engagement. Define solutions to meet performance, capability, and scalability needs.
Must have skills : Python (Programming Language)
Good to have skills : CommerceTools Commerce Platform
Minimum 5 year(s) of experience is required
Educational Qualification : 15 years full time education
Summary: Lead the engineering delivery of GenAI products. Own technical decisions, solution quality, and team execution across front end, back end, and cloud AI services. Mentor developers, standardize patterns, and ensure secure, scalable deployments. Roles & Responsibilities: - Translate business requirements into solution blueprints (LLM selection, RAG architecture, data contracts, API design).
- Own non functional targets (latency, scalability, cost, resilience) and guide performance engineering.
- Establish coding standards for Python/TypeScript enforce test coverage, secure practices, and review discipline.
- Design RAG pipelines at scale: ingestion jobs, metadata schema, hybrid search (embeddings), re ranking.
- Decide cloud service mix and deployment topology across AWS/Azure/GCP optimize token/cost with caching, response shaping, batching.
- Integrate observability (logs, traces, metrics), evaluation (hallucination/toxicity/bias), and responsible AI controls.
- Plan and run CI/CD & MLOps (model/config versioning, feature flags, canary/blue green).
- Mentor engineers unblock delivery collaborate with architects, product, and security. Professional & Technical Skills: - Deep hands on Python + system design for microservices/REST/graphql front end in React/Angular.
- Proven LLM & RAG solutioning: retrieval strategies, grounding sources, prompt/tool orchestration, guardrails.
- Cloud design patterns:
- AWS: Bedrock, Lambda/Step Functions, SageMaker endpoints, Kendra/OpenSearch, CloudWatch.
- Azure: OpenAI, Functions/AKS, Cosmos DB, Azure AI Search, Monitor/Log Analytics.
- GCP: Vertex AI, Cloud Run, BigQuery, AlloyDB, Vertex Search/RAG.
- Security & compliance: OAuth2/OIDC, secret rotation, data residency, PII handling, prompt security.
- Performance & cost engineering for LLMs (token budgets, context packing, streaming).
- Experience leading multi agent systems, workflow engines, and event driven architectures. Additional Information: - Bachelor s/Master s in CS/Engineering (or equivalent).
- Typically 10–14 years total experience 3–6 years in AI/GenAI.
- Demonstrated team leadership across 6–12 engineers.
This job post has been translated by AI and may contain minor differences or errors.
