AI/ML Full Stack Engineer

You are a Senior AI/ML Full Stack Engineer who brings deep hands-on experience building production-grade AI applications with Java or Python. You’‘ve spent 7-10+ years mastering full-stack development and have moved confidently into agentic AI, RAG architectures, and LLM orchestration. You’‘re just as comfortable designing a vector store retrieval pipeline as you are hardening a CI/CD deployment on AWS. You thrive in fast-paced, in-office environments where live coding and hands-on problem solving are part of the culture, and you’‘re excited to bring responsible AI practices - guardrails, evaluation frameworks, and content filtering - into everything you build.

What You’‘ll Do

· Design and build AI/ML applications end-to-end, from architecture through production deployment

· Implement RAG pipelines, including chunking strategies, embedding models, and vector store integration (Pinecone, OpenSearch, pgvector, FAISS)

· Build and orchestrate AI agents using frameworks such as LangChain, LlamaIndex, Semantic Kernel, or CrewAI

· Develop and deploy solutions using AWS Bedrock, Anthropic Claude models, and model invocation APIs

· Apply advanced prompt engineering techniques - system prompts, few-shot, chain-of-thought, tool use, structured outputs

· Build conversational AI experiences, including chatbots (text) and voicebots (speech-to-text, text-to-speech)

· Design and maintain APIs (REST, GraphQL), microservices, and event-driven architectures

· Own CI/CD pipelines, containerization (Docker, ECS/EKS), and infrastructure-as-code for production systems

· Implement evaluation frameworks, guardrails, content filtering, and responsible AI practices across LLM-powered features

· Bachelor’’s degree required

· 10+ years of software development experience (Java or Python), OR 7+ years if entirely full-stack + Agentic AI development experience

· 2+ years hands-on experience building AI/ML applications in production

· Strong proficiency with RAG architectures - chunking strategies, embedding models, vector stores (Pinecone, OpenSearch, pgvector, FAISS)

· Experience with AI orchestration frameworks: LangChain, LlamaIndex, Semantic Kernel, or CrewAI

· Hands-on experience with AWS Bedrock, Anthropic Claude models, and model invocation APIs

· Proven prompt engineering skills - system prompts, few-shot, chain-of-thought, tool use, structured outputs

· Experience building conversational AI: chatbots (text) and voicebots (speech-to-text, text-to-speech)

· Proficiency with AWS services (Lambda, Step Functions, API Gateway, S3, DynamoDB, SQS)

· Experience with CI/CD pipelines, containerization (Docker, ECS/EKS), and infrastructure-as-code

· Strong understanding of API design (REST, GraphQL), microservices architecture, and event-driven systems

· Familiarity with evaluation frameworks for LLM outputs

· Experience with guardrails, content filtering, and responsible AI practices