1 day ago
Remote, United StatesStaff+
Base Salary
$133k - $182k/yr
Responsibilities
- Own the end-to-end development of the enterprise agentic AI platform.
- Design, develop, test, and deploy scalable generative AI capabilities for autonomous multi-step task execution.
- Provide technical direction across GenAI projects and collaborate with solution and enterprise architects on platform architecture.
- Develop retrieval, memory, tool-use, context-engineering, and agent-orchestration patterns for enterprise applications.
- Build internal frameworks and pipelines integrating LLMs and agents with enterprise data sources and services.
- Establish prompt, context, agent, dataset, and model versioning practices and reproducible experimentation workflows.
- Implement automated evaluations, regression suites, observability, guardrails, CI/CD, and LLMOps practices.
- Conduct code, prompt, and context-pipeline reviews and enforce quality, security, scalability, and resilience standards.
- Evaluate GenAI tools and methods and deliver proof-of-concept projects for new models, frameworks, and approaches.
- Mentor and coach engineers and provide non-managerial input on performance, hiring, and promotions.
Requirements
- 7–10 years of progressively complex experience building and scaling enterprise software systems, with recent hands-on GenAI or agentic AI experience in production.
- The posting also describes 10+ years of experience designing, developing, and deploying enterprise-scale technology solutions as an ideal qualification.
- Hands-on experience with prompt engineering, context engineering, RAG, GraphRAG, ReAct, planner/executor, and multi-agent orchestration patterns.
- Proficiency with modern GenAI frameworks and libraries such as LangChain, LangGraph, or Semantic Kernel, or similar tools.
- Experience integrating and adapting LLMs into enterprise applications and working with model-serving runtimes and agent orchestration frameworks.
- Knowledge of transformer-based models, NLP fundamentals, tokenization, embeddings, knowledge representation, multimodal models, function calling, and RLHF/RLAIF.
- Experience with AWS Bedrock, kore.ai, or GCP AI and with containerized and serverless architectures.
- Understanding of LLMOps and AI DevOps practices, including evaluation, versioning, observability, tracing, cost and token monitoring, red-teaming, and guardrails.
- Strong data engineering and architecture experience for curating, chunking, enriching, governing, and securing AI-ready corpora.
- Hands-on experience with vector databases, hybrid search, reranking, knowledge graphs, embedding strategies, semantic layers, metadata, and access controls.
- Experience integrating GenAI solutions through APIs, microservices, and event-driven patterns.
- Proven technical leadership, mentorship, design-review, communication, problem-solving, and enterprise platform delivery abilities.
- Knowledge of AI ethics, safety, security, governance, compliance, prompt injection, data exfiltration, jailbreaks, PII handling, and responsible AI practices.
- Familiarity with enterprise monitoring, tracing, and logging tools such as Splunk, LangFuse, and CloudWatch.
- A bachelor's degree in Computer Science or Data Science is preferred.
Benefits
- Comprehensive medical, dental, and vision coverage.
- Health care and dependent care spending accounts.
- Short- and long-term disability coverage, life insurance, and accidental death and dismemberment insurance.
- Employee and Family Assistance Program and employee discount programs.
- Retirement plan with a generous company match and Employee Stock Purchase Plan.
- Paid Time Off (PTO).
- The position is not sponsorship eligible.
Tech Stack
Categories
