Staff AI Software Engineer
New
Remote-friendly work environment across the United StatesFull-TimeStaff
Salary not disclosed
Apply NowOpens the employer's application page
Job Details
- Experience
- 8+ years of software engineering experience; 2+ years of hands-on experience building and deploying AI/LLM-based systems
- Required Skills
- AWSDockerNode.jsPython.NETMicroservicesLangChain
Requirements
- 8+ years of software engineering experience with strong full-stack or backend development expertise.
- 2+ years of hands-on experience building and deploying AI/LLM-based systems in production environments.
- Proven experience building at least two production AI agents within the past 12 months.
- Strong knowledge of LLM ecosystems (OpenAI, Anthropic, Gemini, Llama, or similar).
- Experience with agent frameworks such as LangChain, OpenAI Agent SDK, or custom orchestration/state machine systems.
- Solid understanding of RAG architectures, vector databases (Pinecone, Weaviate, Chroma, PGVector), and embedding pipelines.
- Proficiency in backend technologies such as .NET, Python, or Node.js, and experience with APIs and microservices.
- Experience working with relational databases (Postgres, SQL Server) and message queues (Kafka, RabbitMQ, SQS, or similar).
- Familiarity with CI/CD pipelines, cloud environments (AWS or Azure preferred), and containerization (Docker).
- Strong communication skills, a proactive mindset, and ability to thrive in fast-paced Agile environments.
Responsibilities
- Design, build, and deploy autonomous AI agents across research, coding, analytics, scheduling, and workflow automation use cases.
- Own end-to-end agent lifecycle including ingestion, reasoning, tool use, action execution, evaluation, and monitoring.
- Architect multi-step agent systems with memory, planning, context tracking, and API orchestration capabilities.
- Build and optimize retrieval-augmented generation (RAG) pipelines, embeddings, vector databases, and knowledge systems.
- Develop scalable agent architectures using frameworks such as LangChain, LlamaIndex, OpenAI Assistants, MCP, or custom orchestration systems.
- Deploy agents as production-grade microservices with observability, guardrails, and performance monitoring.
- Run structured evaluations to improve accuracy, groundedness, latency, and task completion rates.
- Collaborate with product teams to translate requirements into scalable AI-driven solutions and reusable frameworks.
View Full Description & ApplyYou'll be redirected to the employer's site
