Avatar for Salvo Software
Software Developer - C
  • B2B
  • Early Stage
    Startup in initial stages

Expert RAG Engineer

Posted: 1 week ago
Hires remotely in
Remote Work Policy

Remote only

Company Location
Visa Sponsorship

Not Available

RelocationAllowed
Skills
Python
Infrastructure
Technical Leadership
Linux
Caching
Backend
Communication
Performance Tuning
Structured Data
Docker
Microsoft Azure
indexing
Python programming
best practices
Ownership
Evaluation
AWS
Kubernetes
Apache Kafka
Serving
Grounding
Distributed Environments
Latency
Faithfulness
Chunking
XML/XSD
ML
CI/CD
Azure DevOps
Observability
Quantization
CI/CD Pipelines
COST
Milvus
Tracing
Pgvector
Vector Databases
Weaviate
Qdrant
MRR
Embeddings
Ollama
Azure AI Search
Pdfs
Llama.Cpp
GGUF
RAG Pipelines
Model Context Protocol (MCP)
ReRanking
Embedding Models
Cloud Environments
Guardrails
Evaluation Frameworks
Hybrid Retrieval
Open-Source LLMs
Semi-Structured Data
On-Prem Environments
Batching
Architectural Standards
Reference Implementations
Document Ingestion
LLM Serving
NDCG
Remote Environments
Quality Dashboards
recall@K
Air-Gapped Environments
Event-Driven Ingestion
Retrieval Diagnostics
Scanned Documents
Retrieval Quality
Cost Dashboards
Permission-Aware Retrieval
Answer Relevance
Citation
Confidence Handling
Multi-Tenant Retrieval
Office Formats
GPU/CUDA Tuning
Offline Deployments
AI Department
Re-Indexing Pipelines
Production RAG Systems
Metrics-Driven Evaluation
Serving LLMs
GPU/CUDA Troubleshooting

About the job

We are looking for an Expert RAG Engineer to design, build, and own the retrieval-augmented generation systems behind our AI products. Your core work will be architecting production-grade RAG pipelines end to end: ingestion, chunking, embeddings, hybrid retrieval, reranking, evaluation, and serving on top of open-source LLMs (Ollama, llama.cpp) in cloud, on-prem, and air-gapped environments.This is a senior, hands-on role. You'll define RAG architecture standards, make the key technical decisions on retrieval quality, latency, and cost, and provide technical guidance to AI Developers on the team. You'll work closely with engineering, product, and client stakeholders to turn complex knowledge sources into reliable, measurable, and secure AI features.Key ResponsibilitiesRAG Architecture & Engineering (core focus)Design and own end-to-end RAG architectures, from document ingestion to grounded, cited responsesBuild advanced retrieval strategies: hybrid search (dense + BM25/sparse), reranking (cross-encoders), query rewriting/expansion, metadata filtering, and multi-step or agentic retrievalDefine chunking and indexing strategies for diverse sources, including structured and semi-structured data (XML/XSD, Office formats, PDFs, scanned documents)Select, benchmark, and fine-tune embedding models; manage vector databases (pgvector, Qdrant, Weaviate, Milvus, Azure AI Search, or similar) at scaleBuild evaluation frameworks for retrieval and generation quality (recall@k, MRR, nDCG, faithfulness, answer relevance) and run them continuously as part of CI/CDReduce hallucinations through grounding, citation, guardrails, and confidence handlingImplement permission-aware and multi-tenant retrieval so users only access data they're authorized to seeDevelop MCP (Model Context Protocol) integrations that expose RAG systems and internal data sources to LLMs and agentsOptimize LLM serving with Ollama and llama.cpp: quantization (GGUF), GPU/CUDA tuning, batching, caching, and offline/air-gapped deploymentsTechnical LeadershipSet RAG architecture standards, reference implementations, and best practices for the AI departmentReview designs and code, and provide technical guidance to AI DevelopersTranslate client and product requirements into retrieval strategies with clear quality, latency, and cost targetsEvaluate emerging techniques (GraphRAG, long-context vs. retrieval trade-offs, agentic RAG) and recommend what's worth adoptingDevOps & Infrastructure (supporting)Deploy and scale RAG services on Microsoft Azure and AWS using Docker and KubernetesMaintain CI/CD pipelines for AI services (Azure DevOps preferred; GitHub Actions / GitLab CI also used)Build observability for RAG systems: tracing, retrieval diagnostics, latency, cost, and quality dashboardsSupport event-driven ingestion and re-indexing pipelines using Apache KafkaTroubleshoot across the stack - dig into root causes rather than patching symptomsRequirementsExperience & Core RAG Expertise: 6+ years in backend, ML, or infrastructure with 2+ years building production RAG systems, including end-to-end architecture, hybrid retrieval, reranking, chunking, indexing, and evaluation frameworksPython & Vector Databases: Expert-level Python programming combined with deep knowledge of embeddings, vector databases, and metrics-driven evaluationLLM Optimization & Serving: Hands-on experience serving and optimizing open-source LLMs (Ollama, llama.cpp) with quantization, alongside GPU/CUDA troubleshooting and performance tuningDevOps, Infrastructure & MCP: Strong proficiency in Microsoft Azure, AWS, Docker, Kubernetes, Linux, CI/CD pipelines (Azure DevOps preferred), and Model Context Protocol (MCP)Leadership & Collaboration: Strong communication, technical leadership, and ownership to define architectural standards and collaborate effectively in a distributed, remote environment