Generative AI Engineer

Staffworxs; San Francisco (CA); Sur place; USD 160 000 - 260 000; Plein temps

Résumé du poste

Staffworxs is seeking a Generative AI Engineer to join our enterprise AI initiatives. You will design, develop, and deploy GenAI applications to solve complex enterprise problems, spanning LLM infrastructure, agent systems, and integrations with tools like Glean, Gemini Enterprise Apps, or Claude Cowork.

You will build and maintain the LLM gateway, observability capabilities, and agent workflows, while collaborating with Data Science, Product, and Engineering teams to improve developer

Qualifications

• 5+ years of professional software/DevOps/AI infrastructure experience.
• Hands-on experience with large language models in production (prompt design, tool calls, streaming).
• Familiarity with LLM orchestration and gateway tools (LiteLLM, LangChain).

Responsabilités

• Design, develop, and deploy generative AI applications for enterprise problems.
• Contribute to AI platform: LLM infra, agents, and enterprise tools like Glean or Gemini Enterprise Apps.
• Build and maintain LLM gateway with multi-provider routing, caching, and guardrails.
• Develop LLM observability: logging, cost attribution, latency tracking, anomaly detection.
• Create and iterate AI agents/workflows with multi-step tool use and human-in-the-loop.
• Integrate MCP servers to connect agents with tools and data sources (Slack, Jira, databases).
• Design evaluation frameworks for LLM apps and agents; run regression tests and report quality metrics.
• Support VectorDB ingestion pipelines and integration with the AI platform.
• Maintain IaC (Terraform), CI/CD (GitHub Actions), and AWS resources.

Connaissances

Python

LLM APIs

LLM orchestration

AI tooling

Outils

Terraform

GitHub Actions

AWS

LangChain

Glean / Gemini Enterprise Apps

Description du poste

At Staffworxs, we don’t just connect talent — we power transformation. Headquartered in Cedar Park, TX, with teams in Bengaluru and Hyderabad, we combine global reach with deep expertise. Our Digital & Data Analytics practice drives growth and innovation for some of the world’s top brands, who continue to retain us as their trusted partner. If you’re ready to make an impact, you’re in the right place.

Duration: 12+ Months

Job Description

What you'll do

We are seeking a skilled Generative AI Engineer to join our dynamic team who is eager to solve enterprise problems with GenAI. We are embarking upon many critical AI initiatives to help improve employee productivity, developer productivity, and improve business growth. You will be directly involved in innovating and contributing to these highly demanding AI initiatives. You will be responsible for designing, developing, and deploying generative AI applications to solve complex enterprise problems. You are eager to learn, determined to adapt quickly, and comfortable with some ambiguity in requirements.

Responsibility

• Contribute to the design, development, and operations of the organization's AI platform, spanning LLM infrastructure, agent systems, and AI Platforms like Glean (enterprise search platform) or Gemini Enterprise Apps or Claude Cowork
• Support the Glean or any other AI platform by driving sharing, agent development, Glean enablement, and collaboration with the vendors on new feature implementation
• Help build and maintain the LLM gateway (LiteLLM-based), including multi-provider model routing, fallback configuration, caching, cost tracking, FinOps, and guardrail integration (e.g., Amazon Bedrock guardrails)
• Develop and maintain LLM observability capabilities — prompt/response logging, token and cost attribution, latency tracking, failure mode clustering, hallucination detection, and input drift monitoring
• Build, test, and iterate on AI agents and agentic workflows, including multi-step tool use, orchestration patterns, error handling, and human-in-the-loop mechanisms
• Integrate and manage MCP (Model Context Protocol) servers to connect agents and LLM applications with external tools and data sources such as Slack, Jira, databases, and internal APIs
• Design and execute evaluation frameworks for LLM applications and agents — building golden datasets, implementing LLM-as-judge patterns, running regression tests on prompt and model changes, and reporting on quality metrics
• Support VectorDB infrastructure including ingestion pipelines, chunking strategies, retrieval quality measurement, and integration with the broader AI platform
• Maintain infrastructure-as-code (Terraform), CI/CD pipelines (GitHub Actions), and cloud resources (AWS) that underpin the AI platform
• Collaborate with Data Science, Product, and Engineering teams to understand use cases, resolve platform issues, and continuously improve the developer experience for AI application builders across the organization

What you bring

Basic

• 5+ years of professional experience in software engineering, platform engineering, DevOps, or AI/ML infrastructure
• Hands-on experience with LLM APIs and working with large language models in production (prompt design, function/tool calling, streaming, structured outputs)
• Familiarity with LLM orchestration and gateway tools such as LiteLLM, LangChain, or similar frameworks
• Experience with enterprise search or low-code / no-code AI platforms like Glean or Gemini Enterprise Apps — including management, configuration, and developer support
• Experience building or operating AI agents or agentic workflows using frameworks like LangGraph, CrewAI, or custom implementations
• Working knowledge of evaluation approaches for LLM applications — automated test suites, LLM-as-judge, golden dataset management, or A/B comparison infrastructure
• Proficiency in Python and comfort working across backend services, APIs, and scripting
• Experience with AWS cloud services and infrastructure-as-code tools such as Terraform
• Experience building CI/CD pipelines using tools like GitHub Actions, Azure DevOps, or Jenkins

Preferred

• Experience with Model Context Protocol (MCP) — building, integrating, or consuming MCP servers
• Hands-on experience with LLM observability tooling (Arize, Braintrust, Datadog LLM monitoring, LangSmith, or custom tracing solutions)
• Familiarity with RAG architectures — embedding models, vector stores, retrieval strategies, and quality evaluation
• Exposure to prompt injection testing, LLM security, and guardrail implementation
• Experiencing managing a search platform such as Glean, Gemini Enterprise Apps
• Familiarity with real-time inference architectures including serverless patterns with AWS Lambda
• Understanding of semantic caching, intelligent model routing, or FinOps for LLM cost optimization
• Background in a SaaS or enterprise software environment
• Strong troubleshooting skills and the ability to debug across LLM application layers — from prompt behavior to infrastructure
• Solid communication skills and the ability to work cross-functionally with data scientists, product managers, and engineers.

Staffworxs is an Equal Opportunity Employer. We celebrate diversity and are committed to creating an inclusive workplace for all employees, regardless of race, color, religion, gender, sexual orientation, national origin, age, disability, or veteran status.