Generative Ai Engineer

Company: Vaiticka Solution

Location: Malvern, PA

Posted on: September 09

Position: GenAI Engineer

Location: Malvern, PA (Hybrid)

Employment: Full time

Job Description:

We are seeking a highly experienced Senior AI/ML Engineer with deep expertise in Natural Language Processing (NLP), Generative AI, and cloud-native ML systems. This role is ideal for someone who has built production-ready intent detection models, NLG systems, and has strong experience with AWS Bedrock, LangChain and LangGraph. You'll play a key role in architecting and scaling AI-first applications that leverage the latest in LLM, orchestration, and AWS-native services.

Key Responsibilities:

• Design, develop, and deploy intent classification and intent detection models using LLMs and traditional NLP methods.
• Build and optimize Natural Language Generation (NLG) pipelines for chatbot responses, summarization, content creation, or knowledge grounding.
• Architect and implement LangChain and LangGraph based applications for LLM-driven workflows (e.g., autonomous agents, RAG systems).
• Develop scalable machine learning pipelines using the AWS tech stack (e.g., Sagemaker, Lambda, Bedrock, Step Functions, DynamoDB, Athena).
• Integrate and fine-tune foundation models via AWS Bedrock, including Amazon Titan, Anthropic Claude, or Meta Llama.
• Collaborate closely with product managers, ML researchers, and backend engineers to translate business requirements into robust AI solutions.
• Lead experimentation efforts, conduct A/B testing, and ensure continuous evaluation of deployed ML models.
• Mentor junior ML engineers and contribute to best practices in MLOps, model governance, and responsible AI.

Required Qualifications:

• Total 6+ years of experience in machine learning, with a focus on NLP and Generative AI.
• Strong experience building and deploying intent detection, text classification, sequence tagging, and entity recognition models.
• Proficient in LangChain, LangGraph, vector databases (e.g., FAISS, Pinecone), and orchestration of LLM workflows.
• Deep knowledge of AWS Bedrock, Amazon SageMaker, Lambda, DynamoDB, Step Functions, etc.
• Experience working with open-source LLMs (LLaMA, Mistral, Falcon) or commercial APIs (Claude, GPT-4, etc.).
• Proficient in Python, with a solid grasp of ML frameworks such as PyTorch, HuggingFace Transformers, scikit-learn.
• Strong understanding of MLOps practices including model versioning, CI/CD for ML, monitoring, and auto-scaling.
• Bachelor's or Master's in Computer Science, Data Science, or a related field.