TECHNICAL ARCHITECT AI

Overview:

Position Overview

We are seeking a highly skilled Technical Architect (AI) to join our team. In this role, you will leverage your expertise in Generative AI, LLMs, NLP, and machine learning to design and implement innovative AI-driven solutions. The ideal candidate will have a deep understanding of architectural design, RAG pipelines, AI agents, guardrails, and the latest advancements in large language models . You will play a key role in delivering cutting-edge solutions, working with large-scale data, and building systems that enhance automation, intelligence, and efficiency for our clients.

Key Responsibilities

AI Solutioning & Architecture

• Lead the design and implementation of end-to-end AI solutions ensuring scalability, robustness, and efficiency aligned with business needs.
• Architect RAG pipelines using frameworks like LangChain, LlamaIndex, or custom-built stacks .
• Design Agentic AI architectures , including task-based agents, stateful memory, planning-execution workflows, and tool augmentation .

Data Strategy & AI Model Development

• Define and execute data strategies for collection, cleaning, transformation, and integration.
• Fine-tuning & Prompt Engineering: Fine-tuning pre-trained models (e.g., GPT, BERT, etc.) and optimize prompt engineering techniques to drive high-quality, actionable outputs for diverse business use cases.
• Perform embeddings generation, evaluation of outputs , and incorporate human/automated feedback loops .
• Apply advanced NLP techniques such as tokenization, prompt engineering, and query optimization.
• Machine Learning & Deep Learning Models: Build, train, and deploy machine learning models, including deep learning models, for complex AI applications across various domains.

AI Guardrails & Safety

• Build and enforce guardrails for model safety and compliance, including prompt validation, output moderation, and access controls .
• Ensure solutions meet data governance, compliance, and security standards .

Deployment & Cloud-Native Enablement

• Collaborate with teams to deploy solutions in AWS cloud-native environments (Bedrock, Lambda, ECS, SageMaker, CDK).
• Oversee CI/CD pipelines, API integrations, and scalable production deployments .
• Lead LLM provisioning from AWS , balancing performance and cost-effectiveness.
• Deployment & Evaluation: Oversee the deployment of AI models, ensuring smooth integration with production systems, and perform rigorous evaluation of LLMs for accuracy, efficiency, and scalability.

Observability & post-deployment

• Contribute to system observability.
• Support post-deployment monitoring, optimization, and retraining cycles for LLM-driven systems.

Technologies & Frameworks

LLM: Expertise in AWS Bedrock

RAG: LangChain, LlamaIndex, CrewAI, VectorDB

Programming: Python

Cloud Platforms: AWS (Bedrock, SageMaker, Lambda, CDK)

Data & Databases: SQL, NoSQL, Data Lakes, Data Warehouses.

Orchestration & Deployment: CI/CD pipelines, containerized microservices, Kubernetes.

Required Skills & Qualifications

• Proven production experience with RAG pipelines (LangChain, LlamaIndex, or custom stacks).
• Strong understanding of Agentic AI patterns : task agents, memory/state tracking, orchestration.
• Expertise in LLM fine-tuning, embeddings, evaluation strategies, and feedback integration .
• Hands-on experience with AI guardrails (moderation, filtering, prompt validation).
• Proficiency in Python, vector DBs, and LLM APIs .
• Familiarity with CI/CD, API integration, and cloud-native deployments .
• Strong database management skills (SQL & NoSQL).
• Excellent communication, solutioning, and leadership capabilities.