Job Description:
Volie's application is a communication platform built in Golang and VueJS that enables multi-channel communication between users and their customers. We currently have the need to create voice, email, and SMS based AI tools that allow customers to interact with our application and additionally allow us to analyze the content of phone calls, emails, and SMS messages as they occur. We are just beginning to build out our AI team and are looking for someone to lead the efforts within our development team. This position will be the team lead of our conversational intelligence team.
https://www.volie.com
Key Responsibilities:
- Design, develop, and optimize AI prompts to improve customer and user interactions
- Implement prompt engineering techniques such as one-shot learning and chain-of-thought reasoning
- Collaborate with cross-functional teams to integrate prompt designs with our AI platform
- Develop and maintain webhooks and APIs to support prompt functionality
Qualifications
- Bachelor's degree in Computer Science, Engineering, or a related field.
- Strong understanding of AI technology and machine learning algorithms.
- Minimum 5+ years experience as a developer in Golang, Ruby, PHP, Javascript, Python, or C
- Minimum 2+ years experience working with LLMs
- Proficiency in prompt engineering techniques like One-Shot Learning and Chain-of-Thought Reasoning.
- Proficiency in writing Python for API-enabled scripts
- Knowledge of customer service best practices.
- Experience using frontier-scale LLMs (GPT, Claude, Gemini, Llama)
- Fluent in English
AI-Powered Conversational Intelligence Project:
- To effectively contribute to this project, team members need a combination of cloud infrastructure skills (particularly on AWS)
- Strong proficiency in Python; Golang and Javascript are a plus
- Expertise in NLP, and advanced knowledge of AI/ML frameworks like Meta's Llama, PyTorch, others
- Must have practical experience in using LLMs to build robust AI applications, including a solid understanding of agentic frameworks, RAG workflows, and prompt engineering.
- By leveraging these tools and skills, the team will be well-equipped to develop an AI/ML set of product additions that can interact with both our users and the customers of our clients
Technical Tools and Skills Required for the AI-Powered Conversational Intelligence Projects:
1. Cloud Infrastructure: AWS
- The projects will be built on Amazon Web Services (AWS), leveraging its robust cloud infrastructure for scalability, security, and reliability.
- Team members should be proficient in using AWS services such as EC2, S3, Lambda, RDS, and DynamoDB. Familiarity with AWS tools like CloudFormation or others for Infrastructure as Code (IaC) is also essential to ensure automated and consistent deployment of resources.
2. Programming Languages: Python/Golang
- Python is required for developing core components, including AI and machine learning models, data processing pipelines, and backend services.
- Proficiency in Python libraries such as NumPy, Pandas, and scikit-learn is valuable.
- Proficiency in Golang, including creating services, etc is a plus
3. Natural Language Processing (NLP) Experience:
- Team members should have experience in Natural Language Processing (NLP) to understand and interpret various input sources.
- Expertise in text preprocessing, entity recognition, and language modeling techniques, which are crucial for extracting relevant information and generating meaningful and appropriate responses.
4. Experience in Agentic Frameworks, Retrieval-Augmented Generation (RAG) Workflows, and Prompt Engineering:
- Knowledge of Agentic frameworks (frameworks that enable autonomous agent behavior in AI systems) is essential to develop sophisticated AI models that can autonomously generate responses based on input data.
- Proficiency in Retrieval-Augmented Generation (RAG) workflows is required to ensure that the AI models can retrieve relevant information dynamically and generate accurate, relevant, and appropriate responses. Understanding how to implement RAG will help in building an efficient and context-aware AI platform.
- Prompt engineering skills are critical for designing and optimizing the prompts used to interact with the underlying large language models (LLMs). This involves crafting effective prompts that guide the model to generate the desired outputs, improving both accuracy and relevance.
5. Proficiency in Machine Learning Frameworks: PyTorch, HuggingFace
- The team must be adept in using popular ML frameworks like PyTorch for building and training deep learning models. PyTorch is highly flexible and well-suited for experimentation and custom model development.
- Familiarity with the HuggingFace ecosystem, particularly its Transformers library, is crucial for working with pre-trained large language models (LLMs) and fine-tuning them for specific tasks. Experience with HuggingFace’s tools will enable the team to leverage state-of-the-art models and accelerate the development process.
6. Must-Have Experience: Building Applications on Top of Large Language Models (LLMs)
- Team members should have hands-on experience in creating applications that utilize Large Language Models (LLMs) like Llama, or other transformer-based models. This includes knowledge of integrating LLMs into applications, handling model inputs and outputs, and optimizing their performance for specific use cases.
- Practical experience in deploying LLM-based applications in a production environment, managing their scalability, latency, and cost-effectiveness, is also critical to ensure the success of the project.
Please take the time to research our company, watch some of our youtube videos, read some of our blogs, etc before applying. We prioritize culture over everything else and want someone who is genuinely interested in joining our team, not just in need of a job. Although we value your dreams, aspirations, and desire to make the world a better place, we are a for-profit business that is looking for great software developers that want to write great software that helps our customers, our company, and the rest of our team. We are a team of hard-working, scrappy developers that want to work on tough problems with great solutions.
Our hiring process in consists of three steps:
1. Phone interview - 10 basic software and/or development questions
These are designed to be short, off the cuff, and serve as a way for us to rank candidates on the basic skillsets you will need to be successful. You won’t receive any feedback on this call directly and they should take no more than 20 minutes
2. Technical interview
Ascertain your technical knowledge, problem solving abilities, debugging techniques, etc. This interview usually runs about 60 to 120 minutes in length. Please come prepared to demonstrate your work, knowledge, etc
3. Business / operations interview
This will be a panel interview with several members outside the development department that will not be technically focused at all but to determine whether Volie would be a good fit for you organizationally.
Reports to: CTO
Salary: $100k to $140k
Job Type: Full-time
Benefits:
- Health Insurance
- Dental Insurance
- Paid Time Off
- 401k
Please note that background checks are required. This role may have access to highly sensitive data, including: employee data, customer data, company financials, and proprietary product information.