Software Engineering SMTS / LMTS – AI Core

Salesforce

. Design, build, and operate retrieval systems using RAG and hybrid search .

Posted 10/15/2026full-timeRemote • California • United StatesMid-LevelSenior💰 $207,800 - $285,800 per yearWebsite

Core Competencies

Role fit

Core Competencies

Use this summary to align your resume positioning with the role.

Demonstrates expertise in building and operating retrieval systems using RAG and hybrid search, with a strong focus on LLM-powered applications. Proven ability to lead technical design initiatives, mentor engineers, and drive project delivery in high ownership environments.

Highest-signal resume keywords

Retrieval Systems DesignLLM-Powered ApplicationsMulti-Agent OrchestrationBackend Engineering FundamentalsCross-Functional Communication

ATS Keywords

Tailor your resume

Applicant Tracking System Keywords

Tip: use these terms in your resume and cover letter to boost ATS matches.

Hard Skills

RAGHybrid SearchRuby on RailsPythonJavaScriptGoSQLPostgreSQLChunking and Indexing StrategyEmbeddings

Soft Skills

Ownership MindsetCuriosityContinuous LearningAbility to Operate in AmbiguityStrong Communication Skills

Tools & Technologies

AI Application LifecycleAgent and Tool RegistriesEvaluation InfrastructureTracingEvaluation Suites

Industry Keywords

B2B MarketingSales TechnologyEnterprise SaaSContent IngestionConversation Processing

Tech Stack

Tools & technologies

JavaScriptPostgresPythonRDBMSRubyRuby on RailsSQLGo

About the role

Key responsibilities & impact

Design, build, and operate retrieval systems using RAG and hybrid search
Own retrieval initiatives from scoping and design through launch, monitoring, and iteration
Drive technical design for frameworks and platform components used to build production agents
Build multi-agent orchestration, shared primitives for prompts and tools, tracing, and evaluation infrastructure
Diagnose answer quality issues by separating retrieval problems from generation problems
Define and track quality bars and lead improvement efforts
Design ingestion, segmentation, labeling, and retrieval models for documents, knowledge bases, and call transcripts
Build evaluation, observability, rollout, offline evaluation, online monitoring, and regression detection practices
Evaluate solution paths and determine when to trust, redirect, or override model and agent output
Define and track performance and scaling targets for retrieval, indexing, LLM provider usage, and agent orchestration
Ensure reliability and performance of owned systems
Participate in on-call and lead incident resolution
Use coding agents for implementation, testing, refactoring, and documentation
Create reusable workflows, patterns, and tooling to improve team effectiveness
Partner with product, design, and engineering leadership on roadmap, tradeoffs, requirements, and execution plans
Mentor engineers, conduct code reviews, and improve engineering standards, tooling, and processes

Requirements

What you’ll need

Proven experience shipping production AI or backend systems in a high ownership environment, with a recent focus on LLM-powered applications
Expertise building retrieval systems using RAG and hybrid search, including chunking and indexing strategy, embeddings, vector and lexical search, reranking, and measuring retrieval quality
Expertise building developer tooling for production agents, including potential experience with multi-agent orchestration, agent and tool registries, and shared infrastructure for tracing and evaluation
Experience owning platform initiatives from design through adoption across retrieval and indexing, LLM provider integrations, and agent orchestration
Demonstrated technical leadership on significant projects and non-trivial technical problems
Strong track record delivering complex projects with multiple stakeholders, dependencies, or phases
Strong backend engineering fundamentals
Proficiency in Ruby on Rails, Python, JavaScript, or Go
SQL and RDBMS experience; PostgreSQL preferred
Hands-on experience with the AI application lifecycle, including experiment setup, dataset curation, offline evaluation, error analysis, deployment, and online evaluation
Ability to operate in ambiguity and drive clarity
Strong cross-functional communication skills
Ownership mindset and bias for action
Curiosity, continuous learning, and an agent-forward approach
Nice to have: pgvector or other vector indexes and query performance at scale
Nice to have: content ingestion from third-party systems and lifecycle management
Nice to have: conversation or call transcript processing, including PII and consent constraints
Nice to have: evaluation suites for thoroughness and faithfulness
Nice to have: voice or real-time conversational agents
Nice to have: enterprise SaaS, B2B marketing or sales technology, or Salesforce/CRM integrations
Nice to have: startup experience and rapid shipping

Benefits

Comp & perks

Time off programs
Medical insurance
Dental insurance
Vision insurance
Mental health support
Paid parental leave
Life insurance
Disability insurance
401(k)
Employee stock purchasing program
Potential incentive compensation
Potential equity
Reasonable accommodation during the application or recruiting process