Wittify.ai is at the cutting edge of AI-driven solutions, creating advanced conversational AI tools that empower businesses to deliver smarter, faster, and more contextual interactions. We are committed to advancing the capabilities of AI, especially in the realm of conversational agents, knowledge graphs, and retrieval-augmented generation (RAG) systems, to provide real-time, accurate responses that meet complex business needs.
Role Overview:
We are seeking an experienced Machine Learning Engineer with a focus on building conversational AI agents and integrating Retrieval-Augmented Generation (RAG) systems, knowledge graphs, and latency-optimized inference mechanisms. You will design, develop, and deploy text and voice-based conversational agents that leverage RAG and knowledge graphs for highly relevant, context-aware responses. You'll also connect these agents to various tools and data sources to enhance their functionality and performance.
Key Responsibilities:
1. Conversational AI Development:
- Design, develop, and fine-tune text and voice conversational AI agents capable of understanding and generating human-like responses.
- Build NLP/NLU models for intent classification, entity recognition, and context management to support high-quality, responsive conversations.
- Leverage Hugging Face Transformers for advanced language model capabilities, creating rich and nuanced conversational experiences.
2. Retrieval-Augmented Generation (RAG):
- Implement and optimize RAG techniques to retrieve relevant information from knowledge bases and integrate it with generative models.
- Fine-tune RAG models to ensure accurate and efficient retrieval, experimenting with various retrieval methods.
3. Knowledge Graph Design and Integration:
- Design and build knowledge graphs using Neo4j to structure and represent domain-specific data, enhancing conversational context and accuracy in information retrieval.
- Integrate Neo4j-based knowledge graphs with AI models, enabling agents to utilize structured data for precise, contextually aware responses.
- Work closely with data engineering to curate, structure, and maintain knowledge base data.
4. Latency and Inference Optimization:
- Optimize model inference time to ensure low-latency, real-time responses in text and voice interactions.
- Implement efficient data retrieval, caching, and indexing to reduce latency in accessing knowledge graphs and RAG outputs.
- Profile and fine-tune model performance to handle large volumes of requests with minimal lag.
5. Tool Integration and Knowledge Base Connectivity:
- Connect conversational AI agents to external tools and APIs, such as CRMs, databases, and other business systems, to access dynamic data.
- Implement systems to pull data from connected tools and integrate them into conversational workflows.
6. Research and Development:
- Stay updated on advancements in NLP, RAG, knowledge graphs, and conversational AI, experimenting with new techniques to improve agent accuracy and performance.
- Prototype and test new algorithms to enhance conversational quality, knowledge retrieval, and response relevance.
7. Cross-Functional Collaboration:
- Work closely with backend engineers, data engineers, and DevOps to integrate ML models into production environments, ensuring scalability and stability.
- Collaborate with product and UX teams to refine conversational flows and enhance user experience.
Qualifications:
- Educational Background: Bachelor's or Master's degree in Computer Science, Machine Learning, AI, or a related field.
Experience:
- 3+ years in machine learning, with a focus on NLP, NLU, or conversational AI.
- Proven experience in building and deploying conversational agents (text and/or voice).
Technical Skills:
- NLP/NLU: Proficiency in NLP and conversational AI frameworks.
- RAG Implementation: Hands-on experience with Retrieval-Augmented Generation techniques using Vectara, LangChain, and Hugging Face models, including dense embeddings, FAISS, and BM25.
- Knowledge Graphs: Expertise in designing knowledge graph schemas and integrating Neo4j to enable contextual data retrieval.
- Latency Optimization: Experience with optimizing model inference time, caching, indexing, and other latency-reduction techniques.
- Programming Languages: Strong coding skills in Python, with experience in frameworks such as TensorFlow and PyTorch.
- Data Management: Proficient in data preprocessing and knowledge base curation for structured and unstructured data.
Additional Skills:
- API Integration: Ability to connect AI agents to external tools and databases through APIs.
- Cloud & Scalability: Familiarity with cloud infrastructure (AWS, GCP, or Azure) and deploying models in scalable, production-ready environments.
Soft Skills:
- Strong problem-solving skills, attention to detail, and adaptability to new technologies.
- Excellent communication skills and experience collaborating with cross-functional teams.
What We Offer:
- Competitive Compensation: Attractive salary and benefits package.
- Innovative Work Environment: Join a forward-thinking team committed to the latest AI advancements.
- Growth Opportunities: Continuous learning, professional development, and career advancement.
- Flexible Work Environment: Flexible hours and remote work options.
- Impactful Role: Play a crucial part in shaping the future of conversational AI and intelligent retrieval systems.
Wittify.ai is an equal opportunity employer. We celebrate diversity and are committed to creating an inclusive environment for all employees.
Apply now and be a key player in shaping the future of customer engagement!
Together, let's wit-tify the future!
