Company OverviewWBE Consultants LLC is a US-based technology and consulting firm specializing in enterprise digital transformation, with a focus on SAP S/4HANA migrations. Our India development arm, Platinum Consulting & IT Solutions Pvt Ltd, is responsible for building our flagship products.Our product suite includes AMIGO (AI Managed Implementation Governance Office), a Salesforce-native project governance platform, and Belden, an AI-powered project intelligence agent that provides health analysis, risk intelligence, automated reporting, and decision support for complex enterprise programs.The OpportunityWe are looking for an AI/ML Engineer to join our team building Beldens AI engine. You will work alongside a Senior AI/ML Engineer, contributing to the development, testing, and optimization of our RAG (Retrieval-Augmented Generation) pipeline on AWS.Belden is built entirely on AWS (Bedrock, Lambda, S3, Pinecone) and serves as the intelligence layer for AMIGOs Salesforce-based governance data. The core technical challenge is building a production-grade RAG pipeline that can accurately retrieve and reason over deeply hierarchical, relational business data.This is an excellent opportunity for someone with foundational AI/ML experience who wants to go deep on RAG systems and work on a genuinely hard problem making retrieval work over complex enterprise data structures. Youll learn from experienced engineers while contributing meaningfully to a commercial product.Key ResponsibilitiesData Pipeline DevelopmentBuild and maintain data transformation pipelines that convert Salesforce JSON into embedding-ready formatsImplement chunking logic that creates self-contained, contextually rich documents from hierarchical dataDevelop and test Lambda functions for data ingestion, transformation, and retrievalMaintain incremental sync processes between Salesforce (via S3) and PineconeRetrieval & EvaluationExecute retrieval quality tests and document resultsBuild and maintain evaluation datasets (query-answer pairs with ground truth)Implement automated testing pipelines for retrieval accuracyAnalyze retrieval failures and propose improvements to the senior engineerExperiment with embedding models, chunking strategies, and reranking approachesAWS Infrastructure SupportConfigure and maintain Bedrock knowledge bases and agent componentsMonitor Lambda performance, costs, and error ratesImplement logging and observability for pipeline debuggingSupport deployment and testing across development and production environmentsPrompt Engineering & TestingDevelop and refine prompt templates for Beldens five core topicsTest prompt variations and document which approaches produce better outputsImplement guardrails and scope controls to prevent out-of-domain responsesCreate test suites for regression testing prompt changesCollaboration & DocumentationWork closely with the Salesforce development team on data format requirementsDocument pipeline configurations, test results, and operational proceduresParticipate in code reviews and architecture discussionsCommunicate progress and blockers clearly to the teamRequired QualificationsExperience24 years in software engineering with exposure to AI/ML, NLP, or data engineeringHands-on experience with at least one RAG or LLM-based project (production or significant prototype)Familiarity with the RAG pipeline concept: embedding vector store retrieval generationTechnical SkillsPython: Strong proficiency this is your primary working language for Lambda functions and data pipelinesAWS Fundamentals: Working knowledge of S3, Lambda, IAM basics, CloudWatch logsVector Databases: Familiarity with Pinecone, Weaviate, or similar (experience with any vector DB is acceptable)LLM APIs: Experience calling LLM APIs (OpenAI, Anthropic, Bedrock, or similar) and handling responsesData Transformation: Comfortable working with JSON, handling nested structures, and writing transformation logicCore CompetenciesCuriosity about how things work you dig into why something failed, not just that it failedAttention to detail retrieval quality depends on careful implementationClear written communication youll document findings and explain technical issues to the teamWillingness to learn RAG is a fast-evolving field; you should enjoy staying currentPreferred QualificationsAWS Bedrock experience: Familiarity with Bedrock agents, knowledge bases, or model invocationPinecone specifically: Experience with Pinecone indexing, querying, and metadata filteringEvaluation frameworks: Experience with RAG evaluation tools (RAGAS, TruLens, or custom evaluation pipelines)Prompt engineering: Demonstrated ability to craft prompts that produce consistent, well-structured outputsSalesforce or CRM data: Familiarity with Salesforce object structures or similar CRM/ERP data modelsLangChain or similar: Experience with LLM orchestration frameworks (helpful for understanding patterns, though we use custom code)