Staff Software Engineer

Equity Methods•Scottsdale, AZ

About The Position

Staff Software Engineer Equity Methods is seeking a Staff Software Engineer to join our Technology and Innovation group. This is a senior individual contributor role for an engineer who thrives at the intersection of financial services domain expertise and applied AI engineering. You will work directly alongside our Python-based financial consultants to analyze how complex equity compensation and valuation workflows operate today — and redesign them as agentic AI workflows with well-placed Human-in-the-Loop (HITL) checkpoints that preserve the rigor and judgment our clients depend on. This is not a product or infrastructure role. The core of the job is deep collaboration with practitioners who understand the domain, translating that understanding into production AI systems that augment — not replace — expert judgment. The Role in a Nutshell Embed with financial consulting teams to conduct structured workflow analysis and requirements gathering — mapping how SAS and Python-based financial processes actually work before designing any solution. Identify where AI agents can take over routine, high-volume, or pattern-driven steps in financial workflows, and where human review, approval, or override is non-negotiable. Design and implement agentic AI workflows using Amazon Bedrock and N8N, with HITL checkpoints that route exceptions, edge cases, and judgment-dependent decisions to the appropriate human expert. Build and maintain content vectorization and retrieval-augmented generation (RAG) pipelines that give AI agents access to relevant financial context — prior work product, regulatory guidance, client-specific parameters — at runtime. Develop backend services in Python on AWS, with Lambda or FastAPI as the primary compute layers, backed by Postgres, Snowflake and DynamoDB for workflow state management and audit logging of agent decisions, human overrides, and process outcomes. Containerize and deploy agentic services using Docker, maintaining clean separation between workflow components and ensuring deployments are observable, reproducible, and rollback-safe. Build lightweight React interfaces where consultants need to review, approve, or override AI-generated outputs as part of HITL steps. Collaborate with the AI Product Manager on scoping and prioritization, and with the Distinguished Software Engineer on architecture decisions that span multiple workflow systems. Hold yourself accountable for adoption, not just delivery. Measure impact by whether consultants are actually using what you built, whether it saves them time, and whether they come back asking for more. Participate in production ownership of deployed agentic workflows: monitoring agent behavior, catching drift or failure modes, and iterating quickly. We Are: Zealous about exceptional client service and internal collaboration. Agile and execution-focused , with a bias toward action and impact. Growth-oriented and committed to professional development. Feedback-heavy and mentoring-rich , with a culture of continuous improvement. Eager to solve complex, ambiguous problems with creativity and rigor. Hardworking and passionate about building the future of technology-enabled consulting.

Requirements

8–12 years of software engineering experience, with meaningful time spent consulting, working directly with domain experts or business practitioners rather than within a pure product engineering organization.
Demonstrated ability to conduct structured requirements gathering and workflow analysis with non-technical stakeholders — producing precise technical specifications without requiring an intermediary.
Desire to learn to design and implement agentic AI systems, including multi-step agent orchestration, tool use, and Human-in-the-Loop workflow design.
Understanding of LLMs in a production context: prompt engineering, retrieval-augmented generation (RAG), and content vectorization using embedding models (e.g., Amazon Titan, Knowledge Base, PGVector, Elasticsearch, or equivalent).
Strong proficiency in backend service development. Python familiarity is a plus but not required. Expertise in at least one of these languages: Python, Java, Kotlin, Groovy.
Hands-on experience with AWS Lambda as a primary compute pattern, along with DynamoDB, API Gateway, S3, and IAM.
Familiarity with Amazon Bedrock or equivalent managed LLM infrastructure is preferred.
Working knowledge of N8N, UI Path or comparable workflow automation tooling; willingness to become the internal subject-matter expert in N8N or selected workflow platform is expected.
Working knowledge of React is sufficient to build consultant-facing HITL review and approval interfaces.
Comfort operating in an environment where the problem definition evolves as domain understanding deepens — judgment and communication matter as much as execution speed.
Background check required.

Nice To Haves

MBA or Finance degree helpful but not required.

Responsibilities

Embed with financial consulting teams to conduct structured workflow analysis and requirements gathering — mapping how SAS and Python-based financial processes actually work before designing any solution.
Identify where AI agents can take over routine, high-volume, or pattern-driven steps in financial workflows, and where human review, approval, or override is non-negotiable.
Design and implement agentic AI workflows using Amazon Bedrock and N8N, with HITL checkpoints that route exceptions, edge cases, and judgment-dependent decisions to the appropriate human expert.
Build and maintain content vectorization and retrieval-augmented generation (RAG) pipelines that give AI agents access to relevant financial context — prior work product, regulatory guidance, client-specific parameters — at runtime.
Develop backend services in Python on AWS, with Lambda or FastAPI as the primary compute layers, backed by Postgres, Snowflake and DynamoDB for workflow state management and audit logging of agent decisions, human overrides, and process outcomes.
Containerize and deploy agentic services using Docker, maintaining clean separation between workflow components and ensuring deployments are observable, reproducible, and rollback-safe.
Build lightweight React interfaces where consultants need to review, approve, or override AI-generated outputs as part of HITL steps.
Collaborate with the AI Product Manager on scoping and prioritization, and with the Distinguished Software Engineer on architecture decisions that span multiple workflow systems.
Hold yourself accountable for adoption, not just delivery. Measure impact by whether consultants are actually using what you built, whether it saves them time, and whether they come back asking for more.
Participate in production ownership of deployed agentic workflows: monitoring agent behavior, catching drift or failure modes, and iterating quickly.