Software Engineer — Agentic AI Platform

Job Title: Software Engineer - Agentic AI Platform

Location: 100% Remote job (San Francisco CA 94103)

Duration: 6 months

Description:

Work location: Remote across US

About the role

Were building Centralized Agentic AI Framework - a shared platform that brings safe governed cost-aware AI agents into every teams GitLab workflow.

Youll be a hands-on engineer building and extending this platform - writing the Lambdas that orchestrate agents integrating Bedrock with GitLab CI hardening the security and observability layers and shipping new agent capabilities that any team can adopt without re-architecting.

What youll do

• Build agent orchestration - implement Router Lambdas SQS-based queueing and Bedrock Agent invocation
• Integrate with GitLab CI/CD - design . patterns where agent invocations run as pipeline stages consume branch/diff/test context emit artefacts and gate downstream stages on agent pass/fail signals.
• Develop shared Action Groups - build the AWS Lambda-backed tools
• Design Knowledge Bases - iUtilise AWS Bedrock Knowledge Base / OpenSearch / S3 so agents reason over shared organizational context not isolated prompts.
• Implement Bedrock Guardrails - input/output filters sensitive-data scrubbing content/word filters and per-agent permission boundaries enforced by design.
• Implement TokenOps controls - model tiering and routing via an LLM gateway semantic caching context-window management
• Instrument everything in AWS - CloudWatch dashboards audit trails trace logging of every agent invocation (input output decision tokens cost) for compliance and debugging.

Required (3 7 years professional experience)

• Strong Python AWS SDK Python for building production Lambda functions and event-driven services.
• Solid AWS experience: Lambda API Gateway SQS EventBridge IAM Secrets Manager CloudWatch.
• Amazon Bedrock specifically: Agents Action Groups Knowledge Bases Guardrails.
• Hands-on experience integrating with LLM APIs - Bedrock OpenAI Anthropic or similar.
• Familiarity with CI/CD platforms - GitLab CI strongly
• A security mindset: least-privilege IAM secrets handling input validation awareness of prompt injection and data-leak risks in LLM workflows.
• Comfortable with observability - structured logging metrics tracing - and writing code thats debuggable in production.

Nice to have

• Vector search / RAG: OpenSearch embeddings retrieval evaluation.
• FinOps or TokenOps: cost attribution model routing semantic caching batch inference.
• Experience building developer platforms or internal tooling - youve shipped something other engineers depend on daily.
• Familiarity with agent frameworks (Bedrock AgentCore) and their tradeoffs.

How you work

• You write small focused services with clear contracts - not monoliths.
• You treat extensibility as a feature: new triggers/agents/tools shouldnt require touching unrelated layers.
• You think about the developer experience of the teams wholl use your platform not just whether the code runs.
• Youre comfortable with ambiguity - agentic systems are non-deterministic and you debug them empirically.