[VCK] Senior Development Lead (AI +RAG Platform )

Responsibilities

• Lead hands-on development of the AI Extraction Gateway, progressing from Simple RAG to Complex RAG
• Implement and tune the expert-weighted (SME) retrieval layer and structured result validation
• Own confidence score calibration; collaborate with the BA on accuracy rubrics and test evidence
• Drive technical delivery cadence: sprint planning, code reviews, technical risk identification, and team unblocking
• Ensure architectural patterns are implemented consistently across the codebase
• Collaborate with the Data Engineer on ingestion pipeline integration points and vector store schema
• Implement and evolve the query orchestration layer (Python/FastAPI, AWS Lambda/ECS)
• Support the QA Automation Engineer in designing the validation harness for RAG outputs
• Maintain development observability: structured logging, CloudWatch dashboards, X-Ray tracing
• Must-Have Skills & Experience
• 6+ years in software development; minimum 2 years in a tech lead or senior engineering lead capacity
• Strong Python development skills; FastAPI or equivalent async Python framework required
• Hands-on AWS experience: ECS and/or Lambda, API Gateway, DynamoDB, S3, CloudWatch, X-Ray
• Experience with vector databases OpenSearch, Pinecone, Weaviate, or equivalent
• Solid understanding of API design, service decomposition, and clean backend architecture
• AI Experience (Required Not Optional)
• Delivered at least one production RAG, semantic search, or LLM-integrated application end-to-end not a prototype or internal tool
• Practical experience integrating with LLM provider APIs (OpenAI, Anthropic, or Amazon Bedrock) in a production or enterprise configuration
• Working knowledge of chunking strategies, embedding models, retrieval ranking, and prompt engineering in a production context
• Experience with confidence scoring, retrieval evaluation, or hallucination mitigation approaches in a deployed system

Requirements

• Experience with LangChain, LlamaIndex, or similar LLM orchestration frameworks
• Familiarity with OCR pipelines and document extraction tooling (AWS Textract, Tesseract, or equivalent)
• Exposure to multi-tenant data isolation patterns and tenant-scoped encryption key management
• We are accepting applications from LATAM countries
• #LI-DNI

Additional Information

About the Project Software Mind is building a private, tenant-isolated AI assistant for the real estate title and settlement industry. The platform is a retrieval-first (RAG) system that ingests historical email, documents, and structured metadata into a per-tenant vector index, and serves grounded, cited, expert-weighted answers through a chat-style Q&A interface with single sign-on and full audit logging. The platform is AWS-native with a Python/FastAPI backend, Vue.js frontend, OpenSearch/Pinecone vector store, and OpenAI/Anthropic/Bedrock as LLM provider. You will join a senior, cross-functional LATAM-based team where hands-on AI delivery experience not just familiarity is the baseline expectation. You are the technical delivery lead the bridge between architectural intent and day-to-day engineering execution. You own code quality, technical decisions within the team, and the delivery of the core AI Extraction Gateway (Simple and Complex RAG). You are hands-on: coding, reviewing, and unblocking across the Python backend and retrieval layers.

Your Match

How well this role fits your profile.

Company Intel

What employees say

Worked at Softwaremind? Share your experience