GenAI Engineer
- Humac Inc
76 Days Ago
NA
NA
Boston-MA
8-10 Years
Required Skills: AWS, Azure, Kubernetes, Docker, PyTorch, TensorFlow
Job Description
AI Application Development: Build and maintain Python-based AI services using LangChain and CrewAI. Implement RAG-based retrieval and Agentic AI workflows.
• LLM Integration & Optimization: Integrate OpenAI, Bard, Claude, Azure OpenAI APIs. Optimize API calls using temperature, top-p, max tokens, and reduce hallucinations using embedding-based retrieval (FAISS, Pinecone).
• Model Evaluation & Performance Tuning: Assess AI models using Model Scoring, fine-tune embeddings, and enhance similarity search for retrieval-augmented applications.
• API & Microservices Development: Design scalable RESTful API services. Secure AI endpoints using OAuth2, JWT authentication, and API rate limiting.
• Cloud Deployment & Orchestration: Deploy AI-powered applications using AWS Lambda, Kubernetes, Docker, CI/CD pipelines. Implement LangChain for AI workflow automation.
• Agile Development & Innovation: Work in Scrum teams, estimate tasks accurately, and contribute to incremental AI feature releases.
Tech Stack & Tools:
• AI/ML: PyTorch, TensorFlow, Hugging Face, Pinecone
• LLMs & APIs: OpenAI, LangChain, CrewAI
• Cloud & DevOps: AWS, Azure, Kubernetes, Docker, CI/CD
• Security & Compliance: OAuth2, JWT, HIPAA
Preferred Qualifications:
• 8+ years of overall experience with a minimum of 4 years in AI/ML, LLM integrations, and enterprise cloud solutions.
• Proven expertise in GenAI API orchestration, prompt engineering, and embedding retrieval.
• Strong knowledge of scalable AI architectures and security best practices.
• LLM Integration & Optimization: Integrate OpenAI, Bard, Claude, Azure OpenAI APIs. Optimize API calls using temperature, top-p, max tokens, and reduce hallucinations using embedding-based retrieval (FAISS, Pinecone).
• Model Evaluation & Performance Tuning: Assess AI models using Model Scoring, fine-tune embeddings, and enhance similarity search for retrieval-augmented applications.
• API & Microservices Development: Design scalable RESTful API services. Secure AI endpoints using OAuth2, JWT authentication, and API rate limiting.
• Cloud Deployment & Orchestration: Deploy AI-powered applications using AWS Lambda, Kubernetes, Docker, CI/CD pipelines. Implement LangChain for AI workflow automation.
• Agile Development & Innovation: Work in Scrum teams, estimate tasks accurately, and contribute to incremental AI feature releases.
Tech Stack & Tools:
• AI/ML: PyTorch, TensorFlow, Hugging Face, Pinecone
• LLMs & APIs: OpenAI, LangChain, CrewAI
• Cloud & DevOps: AWS, Azure, Kubernetes, Docker, CI/CD
• Security & Compliance: OAuth2, JWT, HIPAA
Preferred Qualifications:
• 8+ years of overall experience with a minimum of 4 years in AI/ML, LLM integrations, and enterprise cloud solutions.
• Proven expertise in GenAI API orchestration, prompt engineering, and embedding retrieval.
• Strong knowledge of scalable AI architectures and security best practices.
