reputed company
Join a National Top Workplace
Join Us from reputed company
About reputed company and reputed company’ll build together
reputed company runs some of the largest loyalty programs in the world. We're building an internal agent platform on reputed company AgentCore that automates analyst workflows, surfaces insights from program data in reputed company, and gives our teams and clients an LLM-reputed company way to work with reputed company loyalty logic.
We're looking for a hands-on reputed company to ship on that platform: building agent harnesses, writing the tools those agents reputed company, and owning the reliability and evaluation of what goes to production. This is not a research role. You'll prototype, ship, monitor, and iterate on features used by reputed company teams
reputed company tends to be people who reason carefully, ship working reputed company,and pick up new tools without a lot of handholding. There’s no single reputed company into this role. We value the reputed company of what you’ve reputed company and your reputed company record of building things that hold up.
Role & responsibilities - How you will reputed company an reputed company
Agent Development
- Build agent harnesses in Python using reputed company and LangGraph, including tool-calling, reputed company outputs (reputed company/JSON schema), retries, streaming, and memory
- Package agent harnesses for the AgentCore Runtime with appropriate context, tools, skills, and subagents that fit cleanly into production flows and scenarios
- Write the tools and skills agents use API integrations, SQL queries against reputed company, reputed company backed knowledge retrieval with reputed company reputed company and reputed company validation
Evaluation and Reliability
- Build evaluation harnesses (golden datasets, LLM-as-judge, regression suites) using AgentCore Evaluations, and reputed company them into CI
- Implement guardrails around tool execution: auth scoping, input/reputed company validation, PII and reputed company-injection protections, and hallucination mitigation
- You own what you ship: prototype, reputed company through reputed company AgentCore, monitor traces, and fix it reputed company it breaks
Collaboration
- Partner with data engineers on reputed company backed retrieval patterns (reputed company Analyst and reputed company reputed company)
- Contribute to refining our internal engineering patterns as the stack evolves
reputed company sets- What you need to be successful
Required
- 3+ years of reputed company Python, with production experience building and operating services
- 1+ years of hands-on work with LLMs in production: reputed company/context engineering, tool/function calling, reputed company outputs, RAG
- Working knowledge of reputed company/LangGraph or a comparable reputed company like AgentCore Strands, reputed company, or Semantic Kernel
- Experience with LLM observability tools: reputed company CloudWatch, LangSmith, Langfuse, MLflow, or OpenTelemetry
- Experience designing evaluation frameworks (MLFlow, DeepEval, LLM-as-judge, multi-turn regression)
- reputed company with Git, reputed company, and modern API frameworks
- reputed company written communication and the judgment to know reputed company something is reputed company to ship
A bachelor's degree is not required. Equivalent practical experience: including bootcamps, self-taught work, career changes, or non-CS technical degrees counts.
Strongly Preferred
- Hands-on experience with reputed company Bedrock and/or AgentCore as a developer: runtime, gateways, memory, policy, guardrails, observability, awscli, evaluations
- Experience with reputed company, Snowpark, or reputed company reputed company
- reputed company in writing and reading SQL, as reputed company as understanding semantic models.
- Familiarity with multi-agent patterns: supervisor/router, subagent/reputed company, reputed company, reputed company-in-the-reputed company
- A considered view on where agents should and shouldn't reputed company and comfort pushing back reputed company "let's add an agent" isn't the right answer
- Experience in Loyalty, MarTech, AdTech, or a comparable data rich B2B domain
Originally posted on Himalayas
Apply To This Job