Saviance ยท 5 months ago
Generative AI Engineer (Senior / Lead / Principal)- Multiple openings
Boston, MA
Full-time
Hybrid
Senior Level, Lead/Staff
8+ years expSaviance is a technology consulting firm headquartered in Boston, MA, specializing in advanced software solutions. They are seeking seasoned Generative AI Engineers to join their innovative team focused on building AI-powered enterprise solutions, working with Large Language Models and deploying scalable AI services.
Information Technology & Services
Responsibilities
Design and develop Python-based GenAI services using frameworks like LangChain and CrewAI, and build Retrieval-Augmented Generation (RAG) and agent-based workflows
Work with OpenAI, Claude, Bard, Azure OpenAI, and other models. Tune prompts using temperature, top_p, and max_tokens. Implement techniques to reduce hallucinations using FAISS, Pinecone, and other vector stores
Fine-tune embeddings, implement hybrid search, and optimize vector-based retrieval performance across enterprise datasets
Develop scalable, secure REST APIs for GenAI services with OAuth2, JWT, and proper rate limiting/access control
Package and deploy services using Docker, Kubernetes, AWS Lambda, or Azure Functions. Automate workflows using CI/CD pipelines and LangChain orchestration tools
Collaborate in a Scrum environment, contribute to sprint planning, provide time estimates, and drive continuous GenAI innovation across product lines
Qualification
Required
8+ to 13+ Years of experience
Deep understanding of LLM frameworks
Python-based AI development
Secure cloud-based deployment strategies
Design and develop Python-based GenAI services using frameworks like LangChain and CrewAI
Build Retrieval-Augmented Generation (RAG) and agent-based workflows
Work with OpenAI, Claude, Bard, Azure OpenAI, and other models
Tune prompts using temperature, top_p, and max_tokens
Implement techniques to reduce hallucinations using FAISS, Pinecone, and other vector stores
Fine-tune embeddings
Implement hybrid search
Optimize vector-based retrieval performance across enterprise datasets
Develop scalable, secure REST APIs for GenAI services with OAuth2, JWT, and proper rate limiting/access control
Package and deploy services using Docker, Kubernetes, AWS Lambda, or Azure Functions
Automate workflows using CI/CD pipelines and LangChain orchestration tools
Collaborate in a Scrum environment
Contribute to sprint planning
Provide time estimates
Drive continuous GenAI innovation across product lines
AI/ML & Embedding: PyTorch, TensorFlow, Hugging Face, Pinecone, FAISS
LLM Ecosystem: OpenAI, LangChain, CrewAI
Programming: Python (primary), TypeScript/JavaScript (a plus)
Cloud & DevOps: AWS, Azure, Kubernetes, Docker, GitHub Actions/CI/CD
Security & Compliance: OAuth2, JWT, HIPAA (if applicable)
Proven track record of leading large-scale AI initiatives (for Principal level)
Strong leadership in AI product delivery (for Lead level)
Strong individual contributor with hands-on experience building and optimizing GenAI solutions (for Senior level)
Preferred
4+ years of hands-on experience in AI/ML and LLM-based solution development
Experience with GenAI orchestration, prompt engineering, and embedding-based retrieval
Deep understanding of enterprise-grade AI security, compliance, and deployment best practices
Background in healthcare or regulated industries is a strong plus
Company
Saviance
Saviance is a modern consulting firm providing a variety of professional services to its clients in the US.
201-500 employees
Funding
Current Stage
Growth StageLeadership Team
Rohit M.
Managing Partner
Company data provided by crunchbase