Principal Engineer - Context Engineering & LLM Optimization

Bank of America; Town of Charlotte (NY); On-site; USD 120,000 - 160,000; Full time

Job summary

Bank of America is looking for a Senior Engineer to define and lead the engineering approach for solutions within a portfolio. This role is critical in delivering significant business outcomes by developing complex technology strategies and approaches.

The ideal candidate will have extensive experience in software and AI engineering, including leading large-scale systems and collaborating with various teams to enhance technology effectiveness. The position is located in New York.

Qualifications

• 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, or AI capabilities.

Responsibilities

• Define and lead the engineering approach for solutions.
• Create and lead the end-to-end test strategy.
• Partner with teams for data improvement and engineering oversight.
• Design context engineering strategies for enterprise applications.

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

Education

Bachelor’s degree in Computer Science, Engineering, Information Systems, Applied Mathematics, or a related technical field

Job description

This role is responsible for defining and leading the engineering approach for solutions at the program or portfolio level, to deliver significant business outcomes.

Responsibilities

• Develop the engineering approach for the entire program/portfolio solution and work with Architecture to develop, analyze, and deliver implementation of technical enablers.
• Lead the planning, definition, and design of complex features which span multiple teams and explore solution alternatives.
• Create ideas on designing complex technology and solution development approaches.
• Lead technical oversight for teams in solution development including design reviews and code within own domain.
• Define the technology tool stack for the solution within a range of internally approved and supported technologies.
• Explore state-of-the-art technologies to improve development efficiencies, quality of test/QA coverage, and release management.
• Lead and be responsible for the end-to-end test strategy, creation, adherence, and integration between teams for a program/portfolio solution.
• Design context engineering strategies for enterprise LLM and RAG applications.
• Define prompt architectures for system prompts, developer instructions, user prompts, retrieved context, tool outputs, conversation history, and structured constraints.
• Optimize context window usage through summarization, compression, ranking, filtering, deduplication, and context prioritization.
• Design retrieval orchestration patterns that determine what data is retrieved, when it is retrieved, and how it is injected into the LLM prompt.
• Partner with RAG database engineers to tune retrieval outputs for downstream reasoning quality.
• Partner with data ingestion engineers to improve source formatting, metadata, and chunk structures for better contextual use.
• Develop patterns for multi-turn conversation memory, session state, user intent preservation, and context refresh.
• Define strategies for grounding, citation handling, source attribution, conflicting evidence resolution, and hallucination reduction.
• Improve the experience for developers, making it easier to deliver industry‑leading solutions while managing work efficiently and with the right controls.
• Advance technology platforms through innovation.
• Reduce risk and improve quality across the technology portfolio by aligning to a single enterprise architecture strategy and delivering governance that enables consistency, integration, and automation.
• Design LLM evaluation frameworks for answer quality, factuality, instruction adherence, relevance, safety, and token efficiency.
• Establish prompt engineering and context engineering standards across product and platform teams.
• Evaluate LLM model behavior across different context sizes, retrieval strategies, and prompt structures.
• Define reusable patterns for agents, tool calling, function calling, dynamic prompt generation, and workflow‑based reasoning.
• Lead technical reviews for LLM application design, prompt safety, and context efficiency.
• 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 Qualifications

• 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 building or architecting production LLM, RAG, or AI assistant systems.
• Deep understanding of how LLMs use prompts, retrieved context, conversation history, system instructions, and tool outputs.
• Strong knowledge of context window management, token budgeting, prompt construction, grounding, and response evaluation.
• Experience with OpenAI, Azure OpenAI, Anthropic, Google Gemini, Meta Llama, or similar LLM ecosystems.
• Experience designing prompt templates, retrieval‑augmented prompts, agent workflows, and tool‑use orchestration.
• Familiarity with vector search, embeddings, reranking, semantic retrieval, and document chunking.
• Experience with automated LLM evaluation, prompt regression testing, and quality measurement.
• Ability to define enterprise standards for reliable, explainable, and secure LLM behavior.
• 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 agentic workflows, multi‑agent orchestration, function calling, or tool‑augmented reasoning.
• Experience with prompt injection mitigation, jailbreak resistance, and secure context handling.
• Experience with token optimization, long‑context models, summarization pipelines, and contextual compression.
• Experience with user personalization, enterprise memory patterns, or domain‑specific copilots.
• Higher‑quality LLM responses with better grounding and reduced hallucination.
• Lower token usage and improved response latency through efficient context construction.
• Standardized prompt and context patterns reused across teams.
• Improved evaluation coverage for LLM behavior, factuality, and instruction adherence.
• Better alignment between retrieved enterprise knowledge and generated responses.
• Enterprise architecture experience with distributed systems design, AI platform engineering, data governance, security, cloud‑native engineering, observability, operational excellence, technical strategy, 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

Work Hours and Shift

• Shift: 1st shift (United States of America)
• Hours per week: 40