Position: GenAI Tool Engineer
Location: Remote
Duration: 6 Months
 
Responsibilities:

• Perform RAG, Grounding, Prompt Engineering in a project: Craft and refine effective prompts to achieve optimal results in various tasks related to product development.
• Excellent attention to detail and organizational skills. Strong programming skills – including in python, ML ecosystem tools, and generative AI.
• Knowledge + Vector Database Development: Design, develop, and implement a robust Vector Database using LLMs and other AI technologies, focusing on capturing information from diverse sources (PDFs, design documents, regulatory requirements, etc.).
• Data Extraction and Structuring: Develop and implement pipelines for extracting data from unstructured documents, including tables, text, and images, structuring the data for LLM training and usage.
• LLM Fine-Tuning and Training: Fine-tune and train generative AI models on client's specific engineering data and domain knowledge to create domain-specific models.
• AI Tool Development: Design and develop a user-friendly GenAI tool that integrates with the knowledge base, allowing engineers to ask questions, generate technical requirements, and perform engineering analyses.
• Technical Requirements Generation: Implement functionality for automatically generating technical requirements from design documents, user stories, and system requirements using LLMs.
• Documentation and Knowledge Transfer: Thoroughly document all development processes, including designs, architecture, code, and training procedures. Provide adequate knowledge transfer to client's internal teams, enabling them to maintain and expand the system.
• Collaboration: Work closely with the Subject Matter Experts and engineers to implement and optimize AI-powered workflows.

Required:

• STEM Background: Minimum 4 year experiences with a Bachelor’s or Master’s with minimum 3 year experience in a STEM field (e.g., Computer Science, Engineering, Physics, Mathematics) with a dedicated focus on AI/ML in the last 1–2 years.
• Proven experience with Google Gemini / Vertex AI (Non-negotiable). Hands-on experience with Gemini 2.5 family of generative AI models and associated technologies, including training, fine-tuning, and deployment.
• Languages: Proficiency in Python, TensorFlow and other Machine Learning and Artificial Intelligence libraries for building LLM agents, tools and MCP servers.
• Context Engineering: Proven experience performing context engineering and prompt tunning. 
• Create REST-APIs to serve AI services and Front-end development for user interface design and development.
• Experience with Vector databases such as Pgvector, AlloyDB etc., graph databases, and other knowledge representation technologies. Clear understanding of Retrieval Augmented Generation (RAG), knowledge representation techniques.
• Unstructured Data Handling: Demonstrated ability to work with unstructured data, including text documents, images, and other media types, and perform data cleaning, preprocessing, and transformation for AI applications (Non-negotiable).

Preferred:

• Experience in creating REST-APIs.
• Familiarity with medical device development regulations (e.g., FDA guidelines, ISO 13485).
• Experience with front-end development for user interface design and development.

Software Skills Required:

• Python, Java, C++, C#) for building LLM agents and tools
• Software Version Control: (e.g., Git, SVN) for collaborative development.
• Testing and Debugging Tools: (e.g., JUnit, pytest) for ensuring the quality of code and LLM agents.
• Cloud computing platforms: Experience with cloud platforms such as AWS, Azure, or GCP is beneficial for working with large language models.
• Version control systems: Git for collaboration and tracking code changes (optional).

 
 
At SPECTRAFORCE, we are committed to maintaining a workplace that ensures fair compensation and wage transparency in adherence with all applicable state and local laws. This position’s starting pay is: $ 55.00/hr.