Ascendion
Website:
ascendion.com
Job details:
Job Title: Gen AI Architect
Work Location: Bengaluru (Hybrid)
Description
We’re looking for an experienced Generative AI Architect to design and scale next-generation AI solutions that power enterprise-grade applications. The ideal candidate will combine deep technical expertise in RAG architectures, Agentic AI systems, and LLM optimization, with a strong grasp of engineering best practices and deployment at scale.
Requirements
12+ years in AI/ML application development, including 2+ years of hands-on experience in Generative AI, RAG frameworks, and Agentic systems.
Responsibilities
- Architect, design, and optimize Retrieval-Augmented Generation (RAG) pipelines using frameworks like LangChain, LlamaIndex, or custom-built stacks.
- Develop Agentic AI systems featuring task-based agents, stateful memory, planning-execution layers, and tool augmentation.
- Fine-tune and evaluate LLMs, generate embeddings, and establish continuous human/automated feedback loops.
- Define and implement robust AI guardrails—including prompt validation, moderation, and compliance controls to ensure safe and reliable operations.
- Lead deployment and orchestration of solutions on cloud-native AI platforms such as Azure OpenAI, AWS Bedrock, or Google Vertex AI.
- Enable observability across AI systems using dashboards, metrics, and post-deployment performance analytics.
- Partner with cross-functional teams (data, platform, security) to translate business needs into scalable AI architectures.
Required Qualifications
- Proven experience building and deploying RAG pipelines (LangChain, LlamaIndex, or equivalent).
- Strong knowledge of Agentic AI patterns—task agents, memory/state management, orchestration flows.
- Expertise in LLM fine-tuning, embeddings, evaluation, and feedback optimization techniques.
- Practical experience implementing AI safety and compliance frameworks (moderation, filtering, prompt validation).
- Proficiency in Python, LLM APIs (OpenAI, Anthropic, Cohere, etc.), and vector databases (e.g., Pinecone, Chroma, Milvus).
- Understanding of CI/CD pipelines, API integration, and cloud-native deployment principles.
Preferred Qualifications
- Experience developing AI systems in regulated domains such as Banking or FinTech.
- Hands-on expertise with cloud AI platforms (Azure OpenAI, AWS Bedrock, Google Vertex AI).
- Knowledge of prompt engineering, RLHF, and LLM observability frameworks.
- Strong communication skills with the ability to lead architecture design reviews and mentor engineering teams.
Click on Apply to know more.