ADP
Website:
adp.com
Job details:
Role Summary
We are seeking a highly skilled and visionary Technical Project Lead / Architect / GenAI Lead to spearhead next-generation AI initiatives. This role demands deep expertise in Large Language Models (LLMs), cloud-native architecture, and strong technical leadership to deliver scalable, secure, and high-performance GenAI solutions primarily on AWS cloud platforms.
Key Responsibilities
- Lead the design, development, and deployment of GenAI solutions leveraging Large Language Models (LLMs) on AWS cloud platforms.
- Architect scalable, event-driven cloud-native solutions using AWS Lambda, SNS, SQS, Step Functions, and related services.
- Drive prompt engineering strategies including prompt versioning, optimization, and chain-of-thought design.
- Oversee fine-tuning, embeddings, and conversational flow development for intelligent, context-aware AI applications.
- Integrate and manage LLM APIs including Azure OpenAI and other emerging AI models.
- Utilize vector databases such as ElasticSearch or OpenSearch for Retrieval-Augmented Generation (RAG).
- Lead model evaluation activities including output analysis, performance tuning, and quality benchmarking.
- Collaborate with data scientists, engineers, and product managers to align AI initiatives with business goals.
- Mentor engineering teams and enforce best practices in GenAI development and cloud architecture.
- Stay current with advancements in AI, cloud services, and LLM frameworks to continuously improve solutions.
Required Skills & Experience
- 6+ years of experience in AWS cloud computing and architecture.
- 4+ years of hands-on experience with Generative AI and Large Language Models.
- Strong programming expertise in Python with frameworks such as FastAPI or Flask.
- Proven experience integrating LLMs into real-world, production-grade applications.
- Deep expertise with AWS services including Lambda, SNS/SQS, Step Functions, and event-driven patterns.
- Mandatory experience with Azure OpenAI services; knowledge of LLaMA and other models is a plus.
- Hands-on experience with vector databases like ElasticSearch, OpenSearch, or similar.
- Advanced proficiency in prompt engineering, prompt optimization, and chain-of-thought techniques.
- Experience using LLM frameworks such as LangChain and LlamaIndex.
- Strong understanding of Retrieval-Augmented Generation (RAG) architectures.
- Expertise in model evaluation, performance tuning, and output quality assessment.
- Excellent leadership, communication, and project management skills.
Education
Bachelor’s or Master’s degree in Computer Science, Engineering, Artificial Intelligence, or a related field.
Click on Apply to know more.