In this role, you will help design, build, and deploy Generative AI and Agentic AI solutions that automate business processes and augment enterprise workflows, working under the guidance of senior engineers. You will support work across the delivery lifecycle — from solution design and prompt/agent development through testing and deployment — partnering closely with automation, data, and platform teams. Responsibilities will include hands-on coding of LLM-powered components, contributing to technical documentation, and building your expertise in GenAI engineering best practices. You will work closely with our team of award-winning business and technical specialists and leaders.
Key Responsibilities:
- Assist in designing and developing LLM-powered applications, including RAG (Retrieval-Augmented Generation) pipelines, agentic workflows, and simple multi-step agents using frameworks such as LangChain and LangGraph, under senior engineer guidance
- Build and maintain retrieval components using vector databases (e.g., ChromaDB) and semantic search to help ground LLM responses in enterprise data
- Apply prompt engineering techniques, with support from senior team members, to improve the accuracy and reliability of LLM-based solutions using hosted (OpenAI API) and offline/self-hosted models
- Support technical discussions with internal stakeholders on solution feasibility and implementation approach, escalating complex decisions to senior engineers
- Help integrate GenAI components with existing enterprise systems via REST APIs, webhooks, and cloud services (AWS Lambda, Azure)
- Contribute to modernizing existing RPA/automation assets (e.g., Blue Prism, code-based automation frameworks) by assisting with AI-driven decisioning features
- Assist in the development and documentation of AI solution deliverables (solution design documents, test/evaluation reports, deployment notes)
- Support CI/CD and monitoring practices for AI applications using tools such as Git, GitHub Actions, Jenkins, and Splunk
- Help identify and flag risks related to model performance, data quality, and security to senior engineers and project leads
Who can apply?
Bachelor's degree in Computer Science, Information Technology, Engineering, or equivalent education and experience
0–3 years of professional software development experience; internships, academic projects, or personal projects involving GenAI/LLMs are a strong plus
Foundational understanding of LLM concepts, prompt engineering, and RAG architectures; hands-on exposure to LangChain or LangGraph is a plus
Proficiency in Python; working knowledge of C#, JavaScript, or SQL is a plus
Basic understanding of REST APIs and cloud platforms (AWS, Azure)
Familiarity with Git/GitHub and basic CI/CD concepts
Exposure to RPA or process automation tools (Blue Prism, UiPath, or Automation Anywhere) is a plus but not required
Willingness to learn IT delivery methodologies (Agile, Lean, ITIL)
Strong problem-solving fundamentals and eagerness to grow technical and delivery skills
Skills you’ll bring
Self-motivated with a strong eagerness to learn and grow in the GenAI/Agentic AI space
Good communicator, comfortable asking questions and seeking feedback from senior team members
Detail-oriented and methodical approach to coding, testing, and documentation
Curious, proactive, and receptive to feedback and mentorship
Team-oriented, collaborating well with senior engineers and cross-functional peers
Adaptable to changing priorities in a fast-evolving technology area
Strong work ethic and ownership of assigned tasks