GenAI Engineer / Forward Deployed Engineer

Would you like to work in a position that provides exceptional benefits and a flexible working environment, using your attention to detail, strong sense of accountability, and ability to communicate with others in your career? Do you want an opportunity for strong work/life balance and career growth while working on a variety of projects with diverse groups of people companywide? If you are looking to make a difference and drive your success, you have come to the right place, and Golden Pear Funding is looking for you!

Our world-class culture is shaped by dedicated Team Members who share a drive to succeed as professionals and together as a company. A great product, amazing people and our stable financial history make Golden Pear a great place to work. We are hiring a GenAI Engineer/Forward Deployed Engineer (FDE) and this is a fully remote position, and you can live anywhere in the US.

Are you an engineer who loves both deep technical architecture and getting your hands dirty with real users? We are hiring a GenAI Engineer / Forward Deployed Engineer (FDE) to build and ship production-grade GenAI systems—and sit directly alongside the teams using them. This is a high-autonomy hybrid role combining deep software engineering with hands-on field work.

What You’ll Do

• Build for Production: Design and deploy multiagent applications using CrewAI, Amazon Bedrock, and modern cloud architectures.
• Embed with Stakeholders: Work directly with business teams to translate messy, halfdefined operational workflows into functional agent designs.
• Own EndtoEnd Delivery: Take broad operational challenges from initial scoping to monitored, evaluated agent teams running live in production.
• Drive Measurable ROI: Iterate rapidly with short feedback loops to align agent performance with business KPIs.

Who You Are: You aren't looking for a pure research or platform role—you want to see your code solve real-world problems today. You excel at bridging technical architecture with operational needs, thrive on direct user feedback, and take pride in making AI actually land inside an organization.

Golden Pear Funding Offers:

• Salary range $160$210 annually DOE
• Competitive PTO plus 40 hours of sick leave yearly wellness days and Holiday pay
• Life, Dental, Vison, EAP, ST and LT disability
• Medical for the employee and family, partial company paid
• EAP
• Summer Fridays
• 401k match up to 4%

Position Summary

Under the guidance and direction of the Chief Technology, Product & AI Officer, the GenAI Engineer / FDE (Forward Deployed Engineer) builds and ships production GenAI systems while working closely with the people who use them. The role is a hybrid of deep engineering and field work: the GenAI Engineer / FDE designs and builds agentic applications using CrewAI, Amazon Bedrock, and other platforms as appropriate, and is embedded directly with business stakeholders to understand their workflows, deploy into their environment, and iterate in alignment with defined KPIs. This is neither a research role nor a pure platform role; it requires a builder who takes ownership, works well with domain experts, and drives projects to deliver measurable results.

Essential Duties and Responsibilities

To perform this job successfully, an individual must be able to perform the following satisfactorily. Reasonable accommodations may be made to enable individuals with disabilities to perform the essential functions.

• Production Agent Delivery: Design, build, and deploy multiagent GenAI applications using CrewAI, Amazon Bedrock, and modern Python tooling, moving beyond pilots and proofsofconcept into live production.
• Deployed Field Work: Embed with business teams and end users to scope ambiguous problems, map existing workflows, and translate them into agent designs with clear autonomy boundaries and humanintheloop checkpoints.
• AWS Architecture: Architect solutions on AWS using Bedrock, Lambda, ECS/Fargate, Step Functions, API Gateway, S3, DynamoDB, and Aurora PostgreSQL.
• RAG Systems: Build retrievalaugmented generation (RAG) systems using Amazon OpenSearch Serverless, Bedrock Knowledge Bases, or pgvector, including chunking, embedding, and retrieval pipeline optimization.
• Evaluation & Quality: Define and build evaluation harnesses, regression suites, and quality metrics so agent behavior can be measured and improved rather than guessed at.
• Guardrails & Security: Implement guardrails, promptinjection defenses, PII filtering, and security controls appropriate to a regulated business environment. Implement secure authentication and authorization using Amazon Cognito, IAM, Secrets Manager, and KMS, following leastprivilege and secure coding practices.
• Observability & Cost Control: Instrument agents for observability and cost control using OpenTelemetry, AWS CloudWatch, structured tracing, and token/spend monitoring dashboards.
• System Integration: Integrate agents with internal systems and external APIs (REST, GraphQL, databases, SaaS applications, and data warehouses) via MCP servers, tool/function calling, and custom connectors.
• CI/CD & IaC: Own endtoend deployment pipelines using GitHub Actions, AWS CodePipeline with Terraform or AWS CDK.
• Field Support & Operations: Monitor deployed applications, troubleshoot production issues, refine prompt/agent logic based on real user feedback, and retrain or update components as needed.
• Research & Recommendations: Run proofofconcepts and feasibility studies to validate new models, frameworks, and tools, and make clear build/buy/defer recommendations. Stay current with advances in LLMs, agent frameworks, and AWS AI services, and bring practical innovations into the codebase.
• Documentation & Mentorship: Document architecture, design decisions, and runbooks; mentor other team members on GenAI patterns, tool usage, and best practices.

Qualifications

To perform this job successfully, an individual must be able to perform each essential duty satisfactorily. The requirements listed below are representative of the knowledge, skill, and/or ability required.

Education & Experience:

• Bachelor’s degree in Computer Science, Software Engineering, or a related technical field (or equivalent practical experience). o5+ years of software engineering experience building production systems in Python.
• 2+ years of experience building and deploying GenAI applications, LLM pipelines, and/or multi-agent systems. oHands-on experience with CrewAI, LangChain, LlamaIndex, AutoGen, or similar agentic frameworks.
• Proven experience with AWS AI/ML infrastructure, specifically Amazon Bedrock and AWS serverless technologies.

Technical Skills:

• Advanced Python proficiency (Pydantic, AsyncIO, FastAPI, pytest). oStrong expertise with AWS services (Bedrock, Lambda, ECS/Fargate, Step Functions, DynamoDB, S3, OpenSearch, IAM, Cognito).
• Deep understanding of RAG architectures, vector databases, embeddings, and retrieval strategies. oHands-on experience with evaluation tools and methodologies (e.g., Ragas, TruLens, DeepEval, or custom evaluation frameworks).
• Familiarity with Model Context Protocol (MCP) and tool-calling patterns.
• Experience with Infrastructure as Code (Terraform or AWS CDK) and CI/CD automation.

Soft Skills & Field Competencies:

• Excellent communication skills with the ability to articulate complex technical details to non-technical business stakeholders. oStrong product mindset and empathy for end users; ability to translate operational pain points into practical software solutions.
• High degree of autonomy, adaptability, and comfort navigating ambiguous, fast-moving environments.

Physical Demands & Work Environment

• Work Environment: 100% remote working environment. Must maintain a reliable home office setup with highspeed internet.
• Physical Demands: Requires prolonged periods of sitting at a desk and working on a computer. Must be able to communicate effectively via video conferencing, chat, and email.
• Effort: The employee must be able to occasionally lift and/or move up to 10 pounds (e.g., laptops, monitors, peripherals).

Note This job description is not intended to be an exhaustive list of duties. Incumbents will follow any other instructions and perform related duties as assigned by their supervisor.

Golden Pear Funding is an Equal Opportunity Employer. We celebrate diversity and are committed to creating an inclusive environment for all employees. All employment decisions are based on business needs, job requirements, and individual qualifications, without regard to race, color, religion, sex, sexual orientation, gender identity or expression, national origin, age, disability status, veteran status, genetic information, or any other status protected by applicable federal, state, or local laws.

About Golden Pear Funding OPCO LLC

Golden Pear Funding is the leading consumer litigation funding firm in the country. We are world-class specialty finance platform deploying over $1B in capital—and we’re investing heavily in AI, data infrastructure. We work with law firms of all sizes to fund personal injury plaintiffs as quickly and efficiently as possible, offering the service, speed, and ease of use attorneys need to focus on pursuing better case outcomes and larger settlements for their clients. Why choose us: • High ownership, low bureaucracy your work actually matters • Work-life balance that’s real sustainable pace, no burnout culture • People-first culture you’re a contributor, not a cog. We don’t treat people like cogs in a wheel. We hire strong individuals, give them ownership, and expect them to make meaningful contributions. Come as your full self and join a diverse, talented, and fun team.