Role: Gen AI Engineer

Location: Boston, MA

Experience: 12+ (Only GC, USC)

Industry: AI/ML, Enterprise Applications, Healthcare (if applicable) 

Role Summary: 

Seeking an experienced GenAI Engineer to integrate LLM APIs, build AI-driven applications, optimize model performance, and deploy AI servicesat scale. The ideal candidate has expertise in Python-based AI development, LLM orchestration, cloud deployment, and enterprise AI integration. 

Key Responsibilities: 

·        AI Application Development – Build and maintain Python-based AI services using LangChain, and CrewAI. Implement RAG-based retrievaland 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 APIs 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