Bellevue, WA
Long Term Contract
What You Will Do:
Primary Focus: Scalable API and service development, data storage, performance optimization, and integration with LLM services. Designing, testing, and optimizing prompts and prompt flows for LLMs and RAG systems.
Must Have: Strong experience in one or more server languages (Java/.NET), REST/GraphQL, relational + caching (Postgres/Redis), and message queues. Practical experience with major LLMs (OpenAI, Anthropic, LLaMA family), prompt templates, prompt chaining and evaluation metrics.
Engineering Practices: TDD/unit integration tests, API documentation, observability.
Integration: Build secure, low latency endpoints for prompt services, manage batching/rate limits, implement auth/ACL.
Deliverables: Well tested service code, API specs, deployment manifests, performance benchmarks, prompt library, A/B evaluation reports, reproducible test harnesses, and integration guides for backend teams.
Safety & Cost Guardrails: Hallucination mitigation, prompt cost optimization, PHI aware handling.
What You Will Bring:
A high impact role with visibility across engineering and product.
Opportunity to lead backend initiatives that bridge scalable service design with GenAI workflows.
A collaborative, growth oriented engineering culture.
Experience working at the intersection of backend systems and LLM integrations.
Opportunity to convert to full time with the client.
PSRTEK is a reputed technology recruitment and IT staffing brand with a global footprint and an admired client base. As an ideas and innovation powerhouse with a culture of excellence, we bring remarkable expertise and deliver powerfully transformative results.