Architect

About Ascendion

Ascendion is a leading provider of AI-powered software engineering solutions that help businesses innovate faster, smarter, and with greater impact. We partner with over 400 Global 2000 clients across North America, APAC, and Europe to tackle complex challenges in applied AI, cloud, data, experience design, and workforce transformation. Powered by more than 11,000 experts, a bold culture, and our proprietary Engineering to the Power of AI (EngineeringAI) approach, we deliver outcomes that build trust, unlock value, and accelerate growth. Headquartered in New Jersey, with 40+ global offices, Ascendion combines scale, agility, and ingenuity to engineer what's next.

Ascendion | Engineering to elevate life | www.ascendion.com

We have a culture built on opportunity, inclusion, and a spirit of partnership. Come, change the world with us:

• Build the coolest tech for the world's leading brands
• Solve complex problems - and learn new skills
• Experience the power of transforming digital engineering for Fortune 500 clients
• Master your craft with leading training programs and hands-on experience

Experience a community of change-makers!

Join a culture of high-performing innovators with endless ideas and a passion for tech. Our culture is the fabric of our company, and it is what makes us unique and diverse. The way we share ideas, learning, experiences, successes, and joy allows everyone to be their best at Ascendion.

About the Role: Gen AI Architect

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.

Want to change the world Let us know.

Tell us about your experiences, education, and ambitions. Bring your knowledge, unique viewpoint, and creativity to the table. Let's talk!