← Back to jobsJob ID col-cmvv3ptze032042b9dekaswge

Public companyPosted 30+ days ago

Software Engineering SMTS / LMTS - AI Core

Full-time
Remote
$172K – $260K/yr
Posted 30+ days ago

Salesforce is hiring a technical leader for the AI Core team, which builds retrieval systems, agent infrastructure, and developer tooling. The role leads initiatives from design through launch and iteration, improves answer quality and operational reliability, and partners across product, design, and engineering.

Posted
30+ Days Ago
Source
salesforce.wd12.myworkdayjobs.com
Sector
Information Technology & AI

Opens the employer's application page in a new tab

Responsibilities

  • Lead retrieval initiatives end to end: Design, build, and operate retrieval systems using RAG and hybrid search (lexical plus vector, reranking, filtering) so agents answer from the right content with the right amount of context. Own delivery from scope and design through launch, monitoring, and iteration
  • Build developer tooling for production agents: Drive technical design for the frameworks and platform pieces our engineers use to build agents, including multi-agent orchestration, shared primitives for prompts, tools, tracing, and evaluation
  • Own answer quality: Diagnose why answers are thin, wrong, or inconsistent by separating retrieval problems from generation problems (prompt, token budget, model choice). Set a quality bar we can test against, and lead the work to reach it
  • Design content and data models: Define how content from documents, knowledge bases, and call transcripts is ingested, segmented, labeled, and retrieved, including the primitives behind freshness, dedupe, source precedence, and internal versus external visibility
  • Make AI changes safe to ship: Build evaluation, observability, and rollout practices (offline evals, online monitoring, regression detection) so we can change prompts, models, and retrieval with confidence. Evaluate multiple solution paths and know when to trust, redirect, or override model and agent output
  • Set performance and scaling benchmarks across the platform we own:
  • Define and track targets for retrieval and indexing, LLM provider usage, and agent orchestration
  • Own operational health: Ensure the reliability and performance of the systems your team owns. Participate in on-call, lead incident resolution for your area, and communicate clearly with the team and stakeholders during incidents
  • Use agentic development to raise leverage: Use coding agents by default for implementation, testing, refactoring, and documentation while holding a high validation bar. Create reusable workflows, patterns, and tooling that raise the effectiveness of your team beyond your own output
  • Partner across functions: Work with product, design, and engineering leadership to shape roadmap, tradeoffs, and requirements, and to translate strategy into concrete execution plans
  • Raise team effectiveness: Mentor engineers, give high-quality code review and technical guidance, and improve standards, tooling, and processes

Qualifications

  • 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 that lets developers build production agents, which can include frameworks for multi-agent orchestration, an agent and tool registry, and shared infrastructure for tracing and evaluation
  • Experience owning platform initiatives from design through adoption, across systems such as retrieval and indexing, LLM provider integrations, and agent orchestration, including driving adoption and evolving the platform as usage grows
  • Demonstrated technical leadership: you lead significant projects, design solutions for non-trivial problems by weighing tradeoffs, and influence architecture and execution beyond your immediate workstream
  • Strong track record delivering complex projects with multiple stakeholders, dependencies, or phases
  • Strong backend engineering fundamentals and proficiency in languages such as Ruby on Rails, Python, JavaScript, or Go, with SQL and RDBMS experience (PostgreSQL preferred)
  • Hands-on experience with the AI application lifecycle: experiment setup, dataset curation, offline evaluation, error analysis, deployment, and online evaluation
  • Comfortable operating in ambiguity and driving clarity: you can frame problems, propose solutions, and align others
  • Strong communicator across functions, able to explain technical ideas to both technical and non-technical audiences and to translate complex concepts into business impact
  • Ownership mindset and bias for action
  • You raise the bar for the team through mentoring, code review, and your own work
  • Curious and continuously learning, with an agent-forward approach to how you build software

Preferred

  • Experience with pgvector or other vector indexes, and with query performance at scale
  • Experience with content ingestion from third-party systems (document stores, knowledge bases, CRM knowledge objects) and the lifecycle problems that follow: sync state, dedupe, source conflict
  • Experience processing conversation or call transcripts, including handling PII and consent constraints
  • Experience designing evaluation suites that score qualities such as thoroughness and faithfulness, not only correctness
  • Experience with voice or real-time conversational agents
  • Experience with enterprise SaaS (especially B2B marketing or sales tech) or Salesforce/CRM integrations
  • Startup experience and rapid shipping
  • Query Performance at Scale
  • Knowledge Bases
  • CRM Knowledge Objects
  • Startup Experience

Required skills

AI Application EvaluationGoJavaScriptLLM-Powered ApplicationsMulti-Agent OrchestrationPythonRAG and Hybrid SearchRetrieval EngineeringRuby on RailsSQL and PostgreSQLpgvector

Full job description

Salesforce is hiring a technical leader for the AI Core team, which builds retrieval systems, agent infrastructure, and developer tooling. The role leads initiatives from design through launch and iteration, improves answer quality and operational reliability, and partners across product, design, and engineering.

Responsibilities

  • Lead retrieval initiatives end to end: Design, build, and operate retrieval systems using RAG and hybrid search (lexical plus vector, reranking, filtering) so agents answer from the right content with the right amount of context. Own delivery from scope and design through launch, monitoring, and iteration
  • Build developer tooling for production agents: Drive technical design for the frameworks and platform pieces our engineers use to build agents, including multi-agent orchestration, shared primitives for prompts, tools, tracing, and evaluation
  • Own answer quality: Diagnose why answers are thin, wrong, or inconsistent by separating retrieval problems from generation problems (prompt, token budget, model choice). Set a quality bar we can test against, and lead the work to reach it
  • Design content and data models: Define how content from documents, knowledge bases, and call transcripts is ingested, segmented, labeled, and retrieved, including the primitives behind freshness, dedupe, source precedence, and internal versus external visibility
  • Make AI changes safe to ship: Build evaluation, observability, and rollout practices (offline evals, online monitoring, regression detection) so we can change prompts, models, and retrieval with confidence. Evaluate multiple solution paths and know when to trust, redirect, or override model and agent output
  • Set performance and scaling benchmarks across the platform we own:
  • Define and track targets for retrieval and indexing, LLM provider usage, and agent orchestration
  • Own operational health: Ensure the reliability and performance of the systems your team owns. Participate in on-call, lead incident resolution for your area, and communicate clearly with the team and stakeholders during incidents
  • Use agentic development to raise leverage: Use coding agents by default for implementation, testing, refactoring, and documentation while holding a high validation bar. Create reusable workflows, patterns, and tooling that raise the effectiveness of your team beyond your own output
  • Partner across functions: Work with product, design, and engineering leadership to shape roadmap, tradeoffs, and requirements, and to translate strategy into concrete execution plans
  • Raise team effectiveness: Mentor engineers, give high-quality code review and technical guidance, and improve standards, tooling, and processes

Preferred

  • Experience with pgvector or other vector indexes, and with query performance at scale
  • Experience with content ingestion from third-party systems (document stores, knowledge bases, CRM knowledge objects) and the lifecycle problems that follow: sync state, dedupe, source conflict
  • Experience processing conversation or call transcripts, including handling PII and consent constraints
  • Experience designing evaluation suites that score qualities such as thoroughness and faithfulness, not only correctness
  • Experience with voice or real-time conversational agents
  • Experience with enterprise SaaS (especially B2B marketing or sales tech) or Salesforce/CRM integrations
  • Startup experience and rapid shipping
  • pgvector
  • Vector Indexes
  • Query Performance at Scale
  • Third-Party Content Ingestion
  • Document Stores
  • Knowledge Bases
  • CRM Knowledge Objects
  • Sync State Management
  • Data Deduplication
  • Source Conflict Resolution
  • Conversation Transcript Processing
  • Call Transcript Processing
  • PII Handling
  • Consent Compliance
  • Evaluation Suite Design
  • Thoroughness Evaluation
  • Faithfulness Evaluation
  • Voice Agents
  • Real-Time Conversational Agents
  • Enterprise SaaS
  • B2B Marketing Technology
  • Sales Technology
  • Salesforce Integration
  • CRM Integration
  • Startup Experience
  • Rapid Execution

Benefits

  • Certain roles may be eligible for incentive compensation
  • Certain roles may be eligible for equity
  • Time off programs
  • Medical, dental, vision, and mental health support
  • Paid parental leave
  • Life and disability insurance
  • 401(k)
  • Employee stock purchasing program

Company

  • AI customer relationship management platform
  • San Francisco, California, USA
  • https://www.salesforce.com/
  • Founded in 1999
  • 10001+ employees

Qualifications

  • 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 that lets developers build production agents, which can include frameworks for multi-agent orchestration, an agent and tool registry, and shared infrastructure for tracing and evaluation
  • Experience owning platform initiatives from design through adoption, across systems such as retrieval and indexing, LLM provider integrations, and agent orchestration, including driving adoption and evolving the platform as usage grows
  • Demonstrated technical leadership: you lead significant projects, design solutions for non-trivial problems by weighing tradeoffs, and influence architecture and execution beyond your immediate workstream
  • Strong track record delivering complex projects with multiple stakeholders, dependencies, or phases
  • Strong backend engineering fundamentals and proficiency in languages such as Ruby on Rails, Python, JavaScript, or Go, with SQL and RDBMS experience (PostgreSQL preferred)
  • Hands-on experience with the AI application lifecycle: experiment setup, dataset curation, offline evaluation, error analysis, deployment, and online evaluation
  • Comfortable operating in ambiguity and driving clarity: you can frame problems, propose solutions, and align others
  • Strong communicator across functions, able to explain technical ideas to both technical and non-technical audiences and to translate complex concepts into business impact
  • Ownership mindset and bias for action
  • You raise the bar for the team through mentoring, code review, and your own work
  • Curious and continuously learning, with an agent-forward approach to how you build software
  • Experience with pgvector or other vector indexes, and with query performance at scale
  • Experience with content ingestion from third-party systems (document stores, knowledge bases, CRM knowledge objects) and the lifecycle problems that follow: sync state, dedupe, source conflict
  • Experience processing conversation or call transcripts, including handling PII and consent constraints
  • Experience designing evaluation suites that score qualities such as thoroughness and faithfulness, not only correctness
  • Experience with voice or real-time conversational agents
  • Experience with enterprise SaaS (especially B2B marketing or sales tech) or Salesforce/CRM integrations
  • Startup experience and rapid shipping

Required skills

  • AI Application Evaluation, Developer Tooling for Production Agents, Go, JavaScript, LLM-Powered Applications, Multi-Agent Orchestration, Python, RAG and Hybrid Search, Retrieval Engineering, Ruby on Rails, SQL and PostgreSQL, pgvector

Preferred skills

  • Experience with voice or real-time conversational agents, Startup experience and rapid shipping

Job details

Employment type

Full-time

Seniority level

Not stated

Date posted

Oct 15, 2026

Work mode

Remote

Job source

salesforce.wd12.myworkdayjobs.com

Company

Public company

Information Technology & AI

AI customer relationship management platform

See all 835 jobs from Public company →
  • San Francisco, California, USA
  • Information Technology & AI
  • 10001+ employees
  • Founded 1999
  • salesforce.com

Similar jobs

Matched on role, skills and location · live jobs only

See more AI Engineer jobs

SUPPLY

3d ago

AI & Marketing Technology Specialist

Full-timeRemoteUnited States$75K – $100K/yr

SUPPLY is an independent media agency hiring an AI & Marketing Technology Specialist to improve agency operations and develop technology-driven capabilities for its teams and clients.

Why similarSame roleJavaScriptPython

Veeam Software

Today

New

Finance AI Engineer

Full-timeRemoteUnited StatesCompetitive

Veeam Software is seeking a Finance AI Engineer to design, build, and deploy reliable AI solutions across Finance functions including Controllership, FP&A, Revenue, Tax, and Treasury.

Why similarSame rolePython

Khan Academy

1d ago

New

Senior Search & AI Discoverability Engineer (12 month contract, 40 hours/week, $85/hour)

Full-timeRemoteUnited StatesCompetitive

Khan Academy is hiring a Senior Search & AI Discoverability Engineer for its Marketing and Acquisition team.

Why similarSame roleGo

Get new AI Engineer jobs by email

Create job alert

Software Engineering SMTS / LMTS - AI Core

Public company · $172K – $260K/yr

Apply on company site