Back to jobs

Principal Engineer - RAG Database & Embeddings Architect

Pay
Pay not listedSimilar roles state $155K–$227K
Work setting
Not stated
Employment
Full-time — employment source
Employment type in the employer’s posting: Full time
From the employer’s posting

What you’ll work on

Full posting
  • Design and own architecture for enterprise RAG data stores and hybrid search layers

  • Define embedding strategies and select embedding models across content types

  • Design vectorization workflows including chunking, indexing, and re-embedding

  • Optimize retrieval quality through reranking, query expansion and metadata boosting

  • Provide design reviews, mentoring and architectural guidance across AI platform teams

From the employer’s posting
Design and own the architecture for enterprise RAG data stores, including vector databases, document stores, metadata stores, and hybrid search layers.
Define embedding strategies across structured, semi-structured, and unstructured content.
Design vectorization workflows including chunking, embedding generation, indexing, versioning, and re-embedding lifecycle management.
Optimize retrieval quality using similarity metrics, reranking, query expansion, metadata boosting, and relevance feedback.
Provide engineering leadership, design reviews, mentoring, and architectural guidance across AI platform teams.

Before you apply

Employer’s visa record
32 H-1B petitions approved in fiscal 2024 and 2025For the employer as a whole. This posting doesn’t say whether the role is sponsored. US Citizenship and Immigration Services.

What you’ll bring

All qualifications

Preferred experience

  • Experience with hybrid retrieval, reranking models, knowledge graphs, or entity-aware retrieval.
  • Experience supporting regulated or enterprise environments with security, compliance, lineage, and privacy requirements.
  • Experience with LLM evaluation, retrieval evaluation, and automated relevance testing.
  • Familiarity with model drift, embedding drift, and re-indexing strategies.
Qualification wording
Experience with hybrid retrieval, reranking models, knowledge graphs, or entity-aware retrieval.
Experience supporting regulated or enterprise environments with security, compliance, lineage, and privacy requirements.
Experience with LLM evaluation, retrieval evaluation, and automated relevance testing.
Familiarity with model drift, embedding drift, and re-indexing strategies.
Education & alternatives
- Strong written and verbal communication skills. - Bachelor’s degree in Computer Science, Engineering, Information Systems, Applied Mathematics, or a related technical field Desired Qualifications:
Apply at Bank of America

Posting record

Report an error

Open 4 monthsWe first saw this posting 140 days ago and it is still up. Roles open this long are often slow to fill or kept open to collect applications.

Status in our records
Live
First seen by us
Jun 29, 2026140 days ago
Recorded sightings
191
Last seen by us
Nov 15, 2026

These dates show when we found the posting. Check the employer’s website to confirm it is still accepting applications.

How this job compares

Pay

$155K–$227K is typical

The middle half of what similar US postings state. This one doesn’t list pay.

From 3,212 postings in the last year. Stated ranges, not salaries paid.

Time since we first saw it

Day 140

Up longer than most. Similar jobs usually come down between day 8 and day 57.

Well past Bank of America’s usual: its jobs come down by about day 23.

From 9,619 similar postings that came down, and 118 of Bank of America’s. Coming down is not always a hire.

Bank of America is hiring

13 open jobs

Open jobs by the week we first saw them, last 12 weeks.

  • Hiring has slowed
  • Takes jobs down quickly
  • 8% of open jobs were reposted
Hiring record

See how this role fits your experience

Add your resume and we’ll mark which of these tools you already use, and point out anything in the posting that could rule you out.

  • Azure
  • Elasticsearch
  • PostgreSQL
  • Hugging Face
Where the posting names them
- Experience with RAG architectures and enterprise-scale knowledge retrieval. - Hands-on experience with platforms such as Azure AI Search, Cosmos DB vector search, Pinecone, Weaviate, Milvus, OpenSearch, Elasticsearch, PostgreSQL/pgvector, or equivalent. - Experience with embedding models from providers such as OpenAI, Azure OpenAI, Cohere, Hugging Face, or open-source model ecosystems.
- Hands-on experience with platforms such as Azure AI Search, Cosmos DB vector search, Pinecone, Weaviate, Milvus, OpenSearch, Elasticsearch, PostgreSQL/pgvector, or equivalent. - Experience with embedding models from providers such as OpenAI, Azure OpenAI, Cohere, Hugging Face, or open-source model ecosystems. - Strong background in distributed systems, database design, API design, and performance tuning.

Your next step

Complete your application on ghr.wd1.myworkdayjobs.com. The employer’s form will show what is required.

Applying through Workday

  • You create an account with each employer before you can upload anything. Every Workday employer has its own account, so one sign-up doesn’t carry over.
  • “Autofill with Resume” comes right after sign-in, before the My Information and My Experience steps. Check every field it fills in those steps, since that’s what recruiters see.
  • Your application status lives in that employer’s Candidate Home, under the same sign-in.

Already applied? Track this application

Job description

View original posting ↗

Job Description:

At Bank of America, we are guided by a common purpose to help make financial lives better through the power of every connection. We do this by driving Responsible Growth and delivering for our clients, teammates, communities and shareholders every day.

Being a Great Place to Work and providing a culture of caring is core to how we drive Responsible Growth. We are intentional about fostering an inclusive workplace where every teammate has the opportunity to succeed, build a career and contribute to our shared success. This includes attracting and developing exceptional talent, recognizing and rewarding performance, and supporting our teammates’ physical, emotional, and financial wellness through affordable, competitive and flexible benefits.

We value the unique perspectives individuals bring from all backgrounds and career paths - whether shaped by military service, community college education, or a wide range of work and life experiences. These journeys foster resilience, leadership and innovation, strengthening our workforce and positively impact the communities we serve.

Bank of America is committed to an in-office culture that supports collaboration, engagement, and career development. Our approach includes clear in-office expectations, while providing an appropriate level of flexibility based on role-specific responsibilities and business needs.

At Bank of America, you can build a successful career with opportunities to learn, grow, and make an impact. Join us!

Job Description:
This job is responsible for defining and leading the engineering approach for solutions at the program or portfolio level, to deliver significant business outcomes. Key responsibilities include continuously improving the design, quality, and reuse of the solution and delivering technology enablers that improve development efficiencies for the solution. Job expectations include familiarity with at least one area of engineering, acting as a “go to” reference across the organization, and applying knowledge to improve technical competencies through recruitment and development activities.

Developer Experience (DevEx) provides enterprise technical standards and common technical services, platforms, and tools that are leveraged by delivery teams across all lines of business. Within the SDLC Software Delivery Lifecycle program, this role leads portfolio product delivery strategy and execution for enterprise software delivery capabilities, ensuring the right investments, operating model, governance, and prioritization are in place to improve how internal technical users build, test, and deliver software at scale.

The RAG Database & Embeddings Architect is responsible for designing, building, and governing the vector database and retrieval architecture that powers enterprise Retrieval-Augmented Generation systems. This role focuses on embeddings, vectorization strategies, semantic search, indexing, metadata modeling, hybrid retrieval, relevance tuning, and performance optimization.

This engineer will define how enterprise knowledge is represented, stored, retrieved, ranked, and refreshed for use by LLM-powered applications.

Responsibilities:

  • Develops the engineering approach for the entire program/portfolio solution and works with Architecture, to develop/analyze/deliver the implementation of technical enablers
  • Leads the planning, definition, and design of the complex features which span multiple teams and explore solution alternatives
  • Creates ideas on designing complex technology and solution development approaches
  • Leads the technical oversight for teams in solution development including design reviews and code within own domain
  • Defines the technology tool stack for the solution within ranged of internally approved and supported technologies
  • Explores state-of-the-art technologies to improve development efficiencies, quality of test/QA coverage, and release management
  • Leads and is responsible for the end-to-end test strategy/creation/adherence, and the integration between teams for a program/portfolio solution
  • Improve the experience for our developers, making it easier to deliver industry-leading solutions, while managing work efficiently and with the right controls
  • Advance our technology platforms through innovation
  • Reduce risk and improve quality across our technology portfolio by aligning to a single enterprise architecture strategy and delivering governance that enables consistency, integration and automation
  • Design and own the architecture for enterprise RAG data stores, including vector databases, document stores, metadata stores, and hybrid search layers.
  • Define embedding strategies across structured, semi-structured, and unstructured content.
  • Evaluate and select embedding models based on accuracy, latency, cost, domain fit, multilingual needs, and operational constraints.
  • Design vectorization workflows including chunking, embedding generation, indexing, versioning, and re-embedding lifecycle management.
  • Implement semantic, keyword, metadata-filtered, and hybrid retrieval patterns.
  • Optimize retrieval quality using similarity metrics, reranking, query expansion, metadata boosting, and relevance feedback.
  • Establish standards for vector schema design, namespace strategy, document lineage, source attribution, and access-control-aware retrieval.
  • Partner with data pipeline engineers to ensure ingestion processes produce high-quality, retrievable content.
  • Partner with context engineers to tune retrieval outputs for downstream LLM consumption.
  • Define observability for retrieval quality, including recall, precision, latency, cost, freshness, and hallucination risk indicators.
  • Lead technical evaluation of vector database platforms and retrieval frameworks.
  • Provide engineering leadership, design reviews, mentoring, and architectural guidance across AI platform teams.
  • Serve as a senior technical authority for enterprise AI platform engineering.
  • Own architecture decisions that impact multiple teams, systems, or domains.
  • Create reusable patterns, reference architectures, standards, and engineering guardrails.
  • Mentor senior engineers and influence technical direction without requiring direct reporting authority.
  • Balance innovation with operational reliability, security, compliance, scalability, and cost management.
  • Communicate complex AI and data engineering concepts clearly to engineering, product, risk, security, and executive stakeholders.

Required Qualification:

  • 10+ years of software engineering, data engineering, platform engineering, or AI engineering experience.
  • 5+ years designing large-scale enterprise systems.
  • 2+ years working with LLM, RAG, vector search, semantic search, or AI platform capabilities.
  • Experience operating systems in regulated, security-conscious, or enterprise-scale environments.
  • Extensive experience designing production-grade search, indexing, or database systems.
  • Strong understanding of vector databases, embeddings, similarity search, approximate nearest neighbor algorithms, and retrieval optimization.
  • Experience with RAG architectures and enterprise-scale knowledge retrieval.
  • Hands-on experience with platforms such as Azure AI Search, Cosmos DB vector search, Pinecone, Weaviate, Milvus, OpenSearch, Elasticsearch, PostgreSQL/pgvector, or equivalent.
  • Experience with embedding models from providers such as OpenAI, Azure OpenAI, Cohere, Hugging Face, or open-source model ecosystems.
  • Strong background in distributed systems, database design, API design, and performance tuning.
  • Experience designing metadata models, access control filtering, document provenance, and auditability.
  • Ability to define engineering patterns and standards used across multiple teams.
  • Proven ability to lead architecture across multiple engineering teams.
  • Strong written and verbal communication skills.
  • Bachelor’s degree in Computer Science, Engineering, Information Systems, Applied Mathematics, or a related technical field

Desired Qualifications:

  • Experience with hybrid retrieval, reranking models, knowledge graphs, or entity-aware retrieval.
  • Experience supporting regulated or enterprise environments with security, compliance, lineage, and privacy requirements.
  • Experience with LLM evaluation, retrieval evaluation, and automated relevance testing.
  • Familiarity with model drift, embedding drift, and re-indexing strategies.
  • High-quality retrieval architecture that improves LLM answer accuracy and reduces hallucinations.
  • Scalable vector database strategy supporting multiple enterprise domains.
  • Clear standards for embeddings, metadata, indexing, and retrieval evaluation.
  • Measurable improvements in retrieval precision, recall, latency, and cost efficiency.
  • Enterprise architecture
  • Distributed systems design
  • AI platform engineering
  • Data governance and security
  • Cloud-native engineering
  • Observability and operational excellence
  • Technical strategy and roadmap development
  • Cross-functional influence
  • Vendor and platform evaluation
  • Production support and continuous improvement

Skills:

  • Automation
  • Influence
  • Result Orientation
  • Stakeholder Management
  • Technical Strategy Development
  • Application Development
  • Architecture
  • Business Acumen
  • Risk Management
  • Solution Design
  • Agile Practices
  • Analytical Thinking
  • Collaboration
  • Data Management
  • Solution Delivery Process

Shift:

1st shift (United States of America)

Hours Per Week: 

40

About Bank of America

People
About 213,000 in 2025.Annual report (SEC Form 10-K)
Company
Listed as BAC.

Demand for Data Leadership roles

New Data Leadership postings at the employers we follow are up 8% over the last 6 weeks compared with the 6 before.

Weekly new Data Leadership postings at the same employers, from the week of August 17 to the week of November 9. The fewest in a week was 752, the most 1,165, and the latest week had 796.
August 17Last week

Each bar is one week of new postings. The darkest bars are the last 6 weeks.

Counted from the hiring pages we’ve followed for at least five weeks, so employers we add don’t look like growth. Updated weekly.

About the role

We file this job under Data Leadership, by the work the posting describes.

Data leaders run data teams or design how a company's data fits together. Managers hire, set priorities and answer for whether the data work pays off; architects choose the systems and the shape of the data.

Expect years of hands-on data work, experience leading people or projects, and the ability to explain tradeoffs to executives.

Unlike a senior engineer or analyst, most of a data leader's week goes to people, planning and decisions rather than building.

US government figures for computer and information systems managers

Median yearly pay, May 2025
$175,140
Expected change, 2025 to 2035
15.8% more jobsagainst 3.5% for all jobs

The government has no code for data leaders, so these figures are for the closest group, computer and information systems managers, which includes data processing and data operations managers.

Source: US Bureau of Labor Statistics, Occupational Employment and Wage Statistics (May 2025) and Employment Projections (2025 to 2035). Occupation code 11-3021.

Source details

View original posting ↗

Source notes

Source excerpts

Selected passages from the saved posting. Check the full description for conditions and exceptions.

Pay

No pay amount identified in the saved description.

Location & working pattern

Charlotte

Developer Experience (DevEx) provides enterprise technical standards and common technical services, platforms, and tools that are leveraged by delivery teams across all lines of business. Within the SDLC Software Delivery Lifecycle program, this role leads portfolio product delivery strategy and execution for enterprise software delivery capabilities, ensuring the right investments, operating model, governance, and prioritization are in place to improve how internal technical users build, test, and deliver software at scale. The RAG Database & Embeddings Architect is responsible for designing, building, and governing the vector database and retrieval architecture that powers enterprise Retrieval-Augmented Generation systems. This role focuses on embeddings, vectorization strategies, semantic search, indexing, metadata modeling, hybrid retrieval, relevance tuning, and performance optimization. This engineer will define how enterprise knowledge is represented, stored, retrieved, ranked, and refreshed for use by LLM-powered applications.
More source context
- Reduce risk and improve quality across our technology portfolio by aligning to a single enterprise architecture strategy and delivering governance that enables consistency, integration and automation - Design and own the architecture for enterprise RAG data stores, including vector databases, document stores, metadata stores, and hybrid search layers. - Define embedding strategies across structured, semi-structured, and unstructured content.

More relevant text appears in the full description.

Work authorization

No clear work-authorization passage found. Eligibility is unconfirmed.

Find answers in the posting

AI
How answers work

AI selects complete passages from this posting. Check them for conditions and exceptions.

Uses this posting and your question. No profile needed.