Simarn Solutions
Job Title: Gen AI Architect
Location: Fremont, CA (Onsite)
Job Type: C2C
Remote: No
Job Summary We are seeking an experienced Senior Technical Lead / Gen AI Architect with strong expertise in Langfuse v3, Azure AI services, and GenAI lifecycle management. The role will involve architecting, implementing, and optimizing advanced GenAI evaluation frameworks, ensuring enterprise-grade reliability, scalability, and observability for AI-driven solutions.
Key Responsibilities
Provide technical leadership to development teams, ensuring best practices, coding standards, and performance optimization in complex GenAI projects.
Architect and deploy Langfuse v3 in production environments, including upgrades from Langfuse v2 with backward compatibility.
Design and build modular components for prompt management, tracing, metrics, evaluation, and playground features using Langfuse v3.
Leverage Langfuse capabilities for Prompt Management versioning, templating, optimization.
Tracing end-to-end visibility of GenAI workflows.
Metrics performance, latency, and usage analytics.
Evaluation automated / manual scoring of outputs.
Playground interactive prompt testing / debugging.
Integrate Azure AI Evaluation SDK into enterprise pipelines for scalable evaluation of GenAI models.
Build reusable components and templates for evaluation across diverse RAG, multi-agent, and GenAI lifecycle workflows.
Ensure scalability, observability, and traceability of evaluation frameworks in both offline and online environments.
Collaborate with cross-functional teams (product, data science, and engineering) to align evaluation metrics with business KPIs.
Conduct feasibility studies, recommend technical alternatives, and ensure compliance with architecture best practices.
Stay current with emerging GenAI evaluation tools and methodologies (e.g., TruLens, W&B, Helicone).
Required Skills & Qualifications
Hands‑on expertise in Langfuse (including v3 features) and integrations.
Proficiency with Azure AI Services and Azure AI Evaluation SDK.
Strong understanding of LLMOps, prompt engineering, and GenAI lifecycle management.
Experience with Retrieval‑Augmented Generation (RAG), fine‑tuning, and multi‑agent orchestration.
Proficiency in Python (TypeScript or other GenAI‑related languages is a plus).
Experience with cloud‑native architectures (Azure preferred).
Familiarity with observability tools, tracing frameworks, and evaluation metrics for GenAI systems.
Excellent communication, documentation, and stakeholder collaboration skills.
Nice to Have
Experience with additional observability tools such as TruLens, Weights & Biases (W&B), Helicone.
Exposure to evaluation standards for enterprise AI adoption.
Knowledge of multi‑cloud and hybrid deployment strategies.
#J-18808-Ljbffr
Location: Fremont, CA (Onsite)
Job Type: C2C
Remote: No
Job Summary We are seeking an experienced Senior Technical Lead / Gen AI Architect with strong expertise in Langfuse v3, Azure AI services, and GenAI lifecycle management. The role will involve architecting, implementing, and optimizing advanced GenAI evaluation frameworks, ensuring enterprise-grade reliability, scalability, and observability for AI-driven solutions.
Key Responsibilities
Provide technical leadership to development teams, ensuring best practices, coding standards, and performance optimization in complex GenAI projects.
Architect and deploy Langfuse v3 in production environments, including upgrades from Langfuse v2 with backward compatibility.
Design and build modular components for prompt management, tracing, metrics, evaluation, and playground features using Langfuse v3.
Leverage Langfuse capabilities for Prompt Management versioning, templating, optimization.
Tracing end-to-end visibility of GenAI workflows.
Metrics performance, latency, and usage analytics.
Evaluation automated / manual scoring of outputs.
Playground interactive prompt testing / debugging.
Integrate Azure AI Evaluation SDK into enterprise pipelines for scalable evaluation of GenAI models.
Build reusable components and templates for evaluation across diverse RAG, multi-agent, and GenAI lifecycle workflows.
Ensure scalability, observability, and traceability of evaluation frameworks in both offline and online environments.
Collaborate with cross-functional teams (product, data science, and engineering) to align evaluation metrics with business KPIs.
Conduct feasibility studies, recommend technical alternatives, and ensure compliance with architecture best practices.
Stay current with emerging GenAI evaluation tools and methodologies (e.g., TruLens, W&B, Helicone).
Required Skills & Qualifications
Hands‑on expertise in Langfuse (including v3 features) and integrations.
Proficiency with Azure AI Services and Azure AI Evaluation SDK.
Strong understanding of LLMOps, prompt engineering, and GenAI lifecycle management.
Experience with Retrieval‑Augmented Generation (RAG), fine‑tuning, and multi‑agent orchestration.
Proficiency in Python (TypeScript or other GenAI‑related languages is a plus).
Experience with cloud‑native architectures (Azure preferred).
Familiarity with observability tools, tracing frameworks, and evaluation metrics for GenAI systems.
Excellent communication, documentation, and stakeholder collaboration skills.
Nice to Have
Experience with additional observability tools such as TruLens, Weights & Biases (W&B), Helicone.
Exposure to evaluation standards for enterprise AI adoption.
Knowledge of multi‑cloud and hybrid deployment strategies.
#J-18808-Ljbffr