AI/ML Software Engineer

Job Description Role: AI/ML Software EngineerLocation: Plano, TXDuration: 6 Months ContractEmployment: W2 (USC/GC Only)Pay Rate: $65-70/hr w2Interview: 2 rounds virtual; final round face-to-faceJob OverviewWe are looking for a Senior Full Stack & Agentic AI Engineer to design, develop, and deploy production-grade AI applications and intelligent agent solutions.The ideal candidate will have strong software engineering and full-stack development experience, along with hands-on expertise in Generative AI, Agentic AI, RAG, LLMs, and conversational AICandidates with 7+ years of software development experience are encouraged to apply, provided their background strongly aligns with Full Stack and Agentic AI development.Key ResponsibilitiesDesign, develop, and deploy scalable Full Stack and Agentic AI applications.Build AI agents, multi-agent workflows, RAG pipelines, and LLM-powered applications.Develop backend services and APIs using Java and/or PythonBuild modern frontend applications and integrate them with AI/ML services.Implement RAG solutions using chunking, embeddings, vector databases, and retrieval techniques.Work with AWS Bedrock and Anthropic Claude models and APIs.Use AI frameworks such as LangChain, LlamaIndex, Semantic Kernel, or CrewAIDevelop conversational AI solutions, including text chatbots and voice-enabled applications.Apply prompt engineering techniques including system prompts, few-shot prompting, tool calling, and structured outputs.Build scalable microservices and event-driven architectures using AWS services.Implement CI/CD, Docker, Kubernetes/EKS/ECS, and Infrastructure as Code.Develop and integrate REST and GraphQL APIsImplement LLM evaluation, observability, guardrails, content filtering, and responsible AI practices.Troubleshoot, optimize, and support production AI applications.Required Qualifications7+ years of hands-on software development experience.Strong proficiency in Java and/or PythonHands-on production experience with Generative AI, LLMs, and Agentic AIStrong experience with RAG architectures, embeddings, chunking, and vector databasesExperience with one or more of:LangChainLlamaIndexSemantic KernelCrewAIHands-on experience with AWS Bedrock and Anthropic ClaudeStrong understanding of prompt engineering and LLM application development.Experience with REST APIs, microservices, and event-driven systemsExperience with AWS services including:LambdaStep FunctionsAPI GatewayS3DynamoDBSQSExperience with Docker, Kubernetes/EKS/ECS, CI/CD, and Infrastructure as CodeExperience building conversational AI, chatbots, or voice-enabled AI applications.Requirements Preferred QualificationsExperience with Pinecone, OpenSearch, pgvector, or FAISSExperience with LLM evaluation and observability frameworks.Experience implementing AI guardrails, content filtering, and responsible AI practices.Experience integrating speech-to-text and text-to-speech technologies.Financial services or banking industry experience.Experience working in enterprise-scale and highly regulated environments.