All Open Jobs
Software Engineer - Agentic AI Platform (37333618)
Job Location
San Francisco, CA
Experience (in Years)
3 - 7
Job Type
Contract W2
Job Openings
Software Engineer - Agentic AI Platform (37333618)
Job Description
Description:
We're building Centralized Agentic AI Framework — a shared platform that brings safe, governed, cost-aware AI agents into every team's GitLab workflow.
You'll 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 you'll do
Build agent orchestration — implement Router Lambdas, SQS-based queueing, and Bedrock Agent invocation
Integrate with GitLab CI/CD — design .
gitlab-ci.yml
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 that's
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 — you've 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 shouldn't require touching unrelated layers.
You think about the developer experience of the teams who'll use your platform, not just whether the code runs.
You're comfortable with ambiguity — agentic systems are non-deterministic, and you debug them empirically.
Job Requirements
Python, AWS SDK Python, Lambda, API Gateway, SQS, EventBridge, IAM, Secrets Manager, CloudWatch, Amazon Bedrock, Agents, Action Groups, Knowledge Bases, Guardrails, LLM APIs, Bedrock API, OpenAI API, Anthropic API, GitLab CI, Least-privilege IAM, secrets handling, input validation, prompt injection awareness, data-leak risk awareness, structured logging, metrics, tracing, debug production code, Vector search, RAG, OpenSearch, embeddings, retrieval evaluation, FinOps, TokenOps, cost attribution, model routing, semantic caching, batch inference, developer platform building, internal tooling, Bedrock AgentCore
About Company
null
Apply for this Job
Apply for this Job
Apply with LinkedIn
Powered by iSmartRecruit.com
