AI/ML Engineer – RAG & Retrieval Systems (Kolkata)

WBE 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.

We are looking for an AI/ML Engineer to join our team building Belden’s 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 AMIGO’s 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. You’ll learn from experienced engineers while contributing meaningfully to a commercial product.

•      Build and maintain data transformation pipelines that convert Salesforce JSON into embedding-ready formats

•      Implement chunking logic that creates self-contained, contextually rich documents from hierarchical data

•      Develop and test Lambda functions for data ingestion, transformation, and retrieval

•      Maintain incremental sync processes between Salesforce (via S3) and Pinecone

•      Execute retrieval quality tests and document results

•      Build and maintain evaluation datasets (query-answer pairs with ground truth)

•      Implement automated testing pipelines for retrieval accuracy

•      Analyze retrieval failures and propose improvements to the senior engineer

•      Experiment with embedding models, chunking strategies, and reranking approaches

•      Configure and maintain Bedrock knowledge bases and agent components

•      Monitor Lambda performance, costs, and error rates

•      Implement logging and observability for pipeline debugging

•      Support deployment and testing across development and production environments

•      Develop and refine prompt templates for Belden’s five core topics

•      Test prompt variations and document which approaches produce better outputs

•      Implement guardrails and scope controls to prevent out-of-domain responses

•      Create test suites for regression testing prompt changes

•      Work closely with the Salesforce development team on data format requirements

•      Document pipeline configurations, test results, and operational procedures

•      Participate in code reviews and architecture discussions

•      Communicate progress and blockers clearly to the team

•      2–4 years in software engineering with exposure to AI/ML, NLP, or data engineering

•      Hands-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 → generation

•      Python: Strong proficiency – this is your primary working language for Lambda functions and data pipelines

•      AWS Fundamentals: Working knowledge of S3, Lambda, IAM basics, CloudWatch logs

•      Vector 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 responses

•      Data Transformation: Comfortable working with JSON, handling nested structures, and writing transformation logic

•      Curiosity about how things work – you dig into why something failed, not just that it failed

•      Attention to detail – retrieval quality depends on careful implementation

•      Clear written communication – you’ll document findings and explain technical issues to the team

•      Willingness to learn – RAG is a fast-evolving field; you should enjoy staying current

•      AWS Bedrock experience: Familiarity with Bedrock agents, knowledge bases, or model invocation

•      Pinecone specifically: Experience with Pinecone indexing, querying, and metadata filtering

•      Evaluation frameworks: Experience with RAG evaluation tools (RAGAS, TruLens, or custom evaluation pipelines)

•      Prompt engineering: Demonstrated ability to craft prompts that produce consistent, well-structured outputs

•      Salesforce or CRM data: Familiarity with Salesforce object structures or similar CRM/ERP data models

•      LangChain or similar: Experience with LLM orchestration frameworks (helpful for understanding patterns, though we use custom code)