Requirements

Bachelor’s degree in Computer Science, Software Engineering, Applied Mathematics, or related quantitative field.
3–5 years of hands-on software engineering experience with proficiency in Java or Python.
Experience with modern full-stack web technologies such as React, TypeScript, FastAPI, and Spring Boot.
Practical experience building Gen AI applications using Google ADK, LangGraph, or equivalent agentic frameworks, vector databases, and AWS Bedrock.
Experience implementing evaluation pipelines and prompt testing using Braintrust, AgentCore Eval, or custom benchmark harnesses.
Working knowledge of core AWS services including Lambda, ECS/Fargate, S3, EventBridge, CloudWatch, and API Gateway.
Solid understanding of standard SDLC tooling, automated testing, Git, Docker, and CI/CD automation.

Nice to Haves

Exposure to financial domain data, investment research workflows, or enterprise content authoring tools.
Understanding of token optimization, prompt caching, and latency reduction strategies.
Familiarity with guardrail frameworks to defend against prompt injection and unauthorized data access.
Experience building asynchronous or event-driven microservices across Java and Python stacks.

Building and maintaining end-to-end full-stack features integrating frontends with backend APIs and microservices using Java or Python.
Implementing and optimizing advanced RAG pipelines and stateful multi-agent workflows with Google ADK, LangChain, LangGraph, AWS Bedrock, or equivalents.
Implementing automated offline and online evaluation suites to assess contextual relevance, groundedness, and reduce hallucination.
Deploying and connecting AI components with enterprise AWS services, configuring Lambda, ECS/Fargate, EventBridge, S3, IAM policies, and API Gateway.
Monitoring model and service performance with CloudWatch and distributed tracing; triaging production incidents and optimizing resource consumption.
Participating in peer code reviews, writing automated tests, maintaining CI/CD pipelines, and documenting integration and data models.
Collaborating in Agile sprints with business stakeholders and cross-functional teams to translate research requirements into technical stories.