Artificial Intelligence (AI) Full Stack Engineer

POSTION TITLE: Artificial Intelligence (AI) Full Stack Engineer

PRIMARY LOCATION: Merrimack, NH (No relocation/<60-minute commute)

SECONDARY LOCATION(s): Boston, MA OR Westlake, TX (No relocation/<60-minute commute)

DURATION OF CONTRACT: 12 months

POSITION DESCIPTION: This domain is the Tech Foundation group. They support all the domains in AM from a tech standpoint. Everyone builds their products off what this team makes. The infrastructure is built and maintained in the Cloud.

CANDIDATE PROFILE:

1.) Experience working with large language model frameworks like Langchain/LlamaIndex.

2.) Understanding of RAG(retrieval-augmented generation) architecture and proven ability to build advanced applications leveraging the architecture.

3.) Experience with prompt engineering and applying techniques to build efficient applications.

4.) Understanding of the large language model development, design, testing, deployment, and familiarity with LLMOps.

INTERVIEW PROCESS: 2 Rounds

1st - 60 minute technical panel

2nd - 60 minute behavioural panel

Description

AI Full Stack Engineer, Cloud Platform

The Role

We are looking for a passionate, self-motivated Software Engineer with strong programming fundamentals, software design and practices to help build and manage our cloud platform. In this role, you will have a great opportunity to marry your full-stack software engineering skills with hands on cloud development. Join our talented team of engineers, designing and building the foundation that propels our business to harness the power of cloud.

The Expertise and Skills You Bring

• Bachelor’s degree or higher in a technology related field (e.g. Engineering, Computer Science, etc.)
• 5 years of software engineering experience
• Certifications preferred: AWS Solutions Architect, AWS Developer, or Kubernetes Application Developer.
• Passion for excellence, automation, innovation, and collaboration.
• Highly motivated to learn new technologies, ways of working, and to adapt every day.
• Bring curiosity and a questioning mind-set to work, injecting new points of view to the team.
• Ability to triage, execute root cause analysis, and be decisive under pressure.
• Ability to creatively solve new, interesting problems in a dynamic environment.
• Ability to work with a variety of individuals and groups, both in person and virtually, in a constructive and collaborative manner and build and maintain effective relationships.
• Ability to act confidently and cautiously in break-the-glass production scenarios to resolve customer outages.
• Solid understanding/experience of networking, virtualization, storage, containers, serverless architecture/framework, cloud IAM controls and policies.
• Strong understanding of Kubernetes concepts/ecosystem and deploying applications into EKS.
• Hands-on experience building and deploying applications using a variety of Amazon Web Services (primarily Cloud Formation, compute, EBS volumes and container).
• Proven experience of building Engineering solutions/automations to enforce engineering standards and best practices.
• Full-stack development experience across distributed applications and services.
• Demonstrated experience with building Flask/FastAPI based REST APIs and applying design patterns to solutions.
• Advanced proficiency in object-oriented python programming and experience working with libraries like numpy, pandas and NLP (natural language processing) frameworks.
• Experience working with large language model frameworks like Langchain/LlamaIndex.
• Understanding of RAG(retrieval-augmented generation) architecture and proven ability to build advanced applications leveraging the architecture.
• Experience working with Vector Databases and being able to query them with programming languages. Bedrock/SageMaker, AWS CloudWhisperer, and integrating large language models like Azure OpenAI, Google Vertex and open-source models.
• Experience with prompt engineering and applying techniques to build efficient applications.
• Understanding of data structures, algorithms and application of core data science techniques and exploratory data analysis (EDA) skills.
• Understanding of the large language model development, design, testing, deployment, and familiarity with LLMOps.
• Experience with fine-tuning large language models is a plus.
• Hands-on experience with containers and container orchestration preferred.
• Experience managing systems using infrastructure as code tools (CloudFormation, OpenTofu, ARM, Ansible …).
• Understanding of versioning and release practices (SCM), code collaboration practices (Git.
• Proficiency with CI/CD tools, especially JenkinsCore.
• Experience executing the Software Development Lifecycle in an agile environment.
• Experience in defining and implementing a comprehensive cloud reliability and observability strategy, ensuring that Client’s cloud systems are always available when our customers need them.