Sr. AI Developer

Job Description

Role: Sr. AI Developer

Team: 5 total (Sr. EE/Manager, Sr. Developer/Lead & 3 Developers)

Location: Sunnyvale (onsite 5x per week)

Duration: 6 months (likely to be extended long/possible conversion)

Meet & Greet Process: 2 steps

Phone screen followed by onsite whiteboarding session

Start Date: ASAP

Mission / About the Role:

This team is building an internal AI-powered engineering productivity platform designed to accelerate hardware design and development workflows. The platform centralizes engineering knowledge—including design best practices, datasheets, hardware specifications, sourcing information, and CAD-related data—and applies agentic AI to help hardware engineers work more efficiently throughout the product development lifecycle.

The Senior AI Developer will lead the design, development, and productionization of high-quality agentic AI systems that integrate enterprise data sources, leverage AWS Bedrock and modern GenAI frameworks, and deliver measurable productivity gains for engineering teams. This role is heavily focused on AI evaluations, accuracy, security, and scalability, ensuring engineers can trust the recommendations and outputs generated by the platform.

Unlike customer-facing AI products, this role is focused on enabling internal engineering teams and improving hardware design productivity through intelligent workflows, retrieval systems, and agent-based automation.

Day-to-Day Responsibilities:

Agentic AI Platform Development

Design, build, and maintain production-grade agentic AI workflows using AWS Bedrock and modern AI frameworks.

Develop AI systems that combine enterprise knowledge, engineering documentation, and internal data sources to support hardware engineering workflows.

Implement multi-step reasoning, tool usage, and autonomous task execution within agentic workflows.

Design and optimize prompts, agent architectures, and evaluation frameworks to maximize AI performance and accuracy.

RAG & Knowledge Systems

Build and maintain Retrieval-Augmented Generation (RAG) solutions using embeddings, vector databases, and knowledge bases.

Develop data ingestion, transformation, and indexing pipelines for engineering documentation, design artifacts, and technical datasets.

Design retrieval strategies across structured and unstructured data sources, including graph and search-based retrieval systems.

Continuously improve retrieval quality, ranking, and response accuracy.

Engineering Productivity & Stakeholder Engagement

Partner with hardware engineers, data owners, and cross-functional stakeholders to identify productivity opportunities and prioritize features.

Gather feedback from engineering users and incorporate findings into future platform enhancements.

Help define product direction, roadmap priorities, and long-term architecture for the AI platform.

Serve as a technical leader, helping break down complex initiatives into executable workstreams.

Platform Reliability, Security & Operations

Implement Human-in-the-Loop (HIL) workflows, validation mechanisms, and governance controls.

Design secure AI systems using enterprise security best practices, including IAM, encryption, audit logging, and data protection controls.

Build scalable backend services, APIs, and microservices supporting AI workflows.

Debug, test, monitor, and optimize deployed AI solutions for performance, reliability, and cost efficiency.

Support CI/CD pipelines and production deployment processes for AI applications.

Required Qualifications:

Core AI & Agentic Development Experience

Proven experience building and deploying production-grade agentic AI systems.

Strong hands-on experience with AI workflow development using AWS Bedrock or comparable cloud AI platforms.

Experience building Retrieval-Augmented Generation (RAG) systems using embeddings, vector databases, and enterprise knowledge sources.

Experience implementing agentic workflows, multi-step reasoning, tool usage, and autonomous task execution.

Familiarity with Model Context Protocol (MCP) and integrating external tools and data sources into AI workflows.

Experience designing evaluation frameworks and validation mechanisms for AI systems.

Software Engineering & Backend Development

Strong Python development skills.

Experience building backend services, APIs, and microservices.

Experience with Flask or similar Python web frameworks.

Strong understanding of software engineering best practices, testing, debugging, and code quality.

Experience working with CI/CD pipelines and modern software delivery processes.

Cloud & Data Engineering

Experience with cloud-native application development in AWS or similar cloud environments.

Experience building data ingestion, transformation, and indexing pipelines.

Knowledge of AWS services including: Bedrock, Lambda, Step Functions, EventBridge, S3, DynamoDB, Kendra, Neptune (or similar graph databases)

Experience designing graph-enhanced or hybrid RAG architectures.

Security & Governance

Experience implementing Human-in-the-Loop (HIL) workflows and AI governance controls.

Understanding of secure AI system design, including:

IAM and least-privilege access

Encryption and key management

Audit logging

Data protection and PII handling

Experience designing reliable distributed systems and asynchronous workflow orchestration.

Candidate Profile

Demonstrated hands-on experience using agentic AI tools in real-world development environments.

Strong understanding of how to maximize AI effectiveness through prompt engineering, workflow design, and agent orchestration.

Ability to work independently, define technical direction, and collaborate effectively with cross-functional stakeholders.

Seniority measured by depth of relevant AI and agentic development experience rather than total years of software engineering experience.

Nice-to-Haves:

Experience with LangChain, LangGraph, LlamaIndex, Hugging Face, or similar AI frameworks.

Experience building agentic reasoning loops with tool usage through MCP.

Experience implementing HIL clarification workflows and human approval checkpoints.

Infrastructure-as-Code experience using AWS CDK (TypeScript preferred).

Familiarity with model governance frameworks, content classification, and AI safety controls.

Experience with dependency scanning, vulnerability management, and security gates in CI/CD pipelines.

Experience working in monorepo or multi-package development environments.

Background supporting engineering productivity tools, developer platforms, or internal engineering enablement initiatives.

Experience supporting hardware engineering, CAD systems, or engineering knowledge management platforms.

Data science or machine learning background with experience evaluating model performance and accuracy.