FDE Engineer (AI Heavy)
CodeRound is hiring for this role.
- Senior AI Engineer
- Applied AI
- Generative AI
- Large Language Models
- LLMs
- AI Agents
- Agentic AI
- Multi-Agent Systems
- LLM Orchestration
- LangChain
- LangGraph
- Python
- Retrieval-Augmented Generation
- RAG
- Vector Databases
- Embeddings
- Semantic Search
- Reranking
- LLM Evaluation
- AI Evals
- Hallucination Reduction
- LLMOps
- MLOps
- Prompt Engineering
- Tool Calling
- Asynchronous Workflows
- SQL
- Snowflake
- Enterprise AI
- API Integration
- Model Optimization
- Latency Optimization
- Cost Optimization
- Llama
- Mistral
- Ray
- Kubeflow
- Distributed Computing
- AI Architecture
We're looking for a Senior AI Engineer to architect and build reliable, production-grade AI agents that solve complex enterprise problems. You'll own end-to-end agentic workflows, combining LLM orchestration, RAG pipelines, automated evaluation, and performance optimization to transform experimental AI solutions into scalable enterprise systems. This role offers the opportunity to drive AI architecture, establish engineering best practices, and build intelligent systems that automate enterprise workflows, integrate complex data systems, and solve real-world business challenges.
What you'll do
- Architect and develop complex, multi-agent systems using LangGraph, LangChain, or equivalent frameworks to automate enterprise workflows and execute long-running, asynchronous tasks.
- Own the end-to-end lifecycle of AI agents, from system architecture and prompt engineering to deployment, monitoring, evaluation, and continuous improvement.
- Design and implement automated evaluation pipelines to measure agent accuracy, hallucination rates, task completion, and reliability before and after production deployment.
- Build, optimize, and scale RAG pipelines by improving chunking strategies, retrieval algorithms, embedding quality, reranking, and vector search performance.
- Optimize inference costs and latency by selecting appropriate models, improving orchestration strategies, and balancing performance with operational efficiency.
- Collaborate with product and engineering teams to translate ambiguous enterprise requirements into concrete agent behaviors, tool definitions, execution plans, and reliable workflows.
- Integrate AI agents with enterprise systems, databases, APIs, and existing infrastructure to enable intelligent automation and end-to-end task execution.
- Establish LLMOps best practices for tracing, monitoring, debugging, versioning, and evaluating AI systems in production.
- Mentor junior AI engineers, lead code reviews, and define engineering standards for building reliable, maintainable, and scalable LLM-powered applications.
Must have
5+ years of overall software engineering experience, with significant recent experience in Applied AI, Generative AI, or LLM-based systems. Expert-level Python programming skills, with the ability to write clean, modular, testable, and production-quality code. Strong hands-on experience building and deploying production-grade LLM applications using orchestration frameworks such as LangChain, LangGraph, or equivalent technologies. Experience designing complex agentic workflows involving multi-agent orchestration, tool calling, state management, asynchronous execution, and long-running tasks. Strong understanding of Retrieval-Augmented Generation (RAG), including document chunking, embedding generation, retrieval strategies, reranking, and vector search optimization. Proven experience designing automated LLM evaluation frameworks to measure output accuracy, hallucinations, task completion rates, and overall system reliability. Strong understanding of data systems, including SQL, relational databases, data pipelines, and vector databases, with the ability to work with complex enterprise data. Experience with LLMOps or MLOps practices, including tracing, monitoring, debugging, prompt and chain versioning, and production performance evaluation. Strong problem-solving and architectural skills, with the ability to balance model complexity, system reliability, latency, and cost while translating ambiguous business requirements into practical AI solutions.
Good to have
Experience fine-tuning or adapting open-source foundation models such as Llama or Mistral for specialized enterprise use cases. Background in traditional Machine Learning, Natural Language Processing (NLP), or deep learning. Experience with distributed computing and ML infrastructure frameworks such as Ray or Kubeflow. Familiarity with enterprise data platforms and modern data stacks, including Snowflake and large-scale data processing systems. Experience optimizing LLM inference, token consumption, throughput, and response latency in production environments. Exposure to agent observability and evaluation tools such as LangSmith, Arize Phoenix, or equivalent platforms. Experience building AI agents that interact with enterprise systems such as ERPs, CRMs, databases, APIs, and internal business applications. Previous experience as a founding engineer or in an early-stage startup, with the ability to operate independently in ambiguous environments. Experience mentoring engineers, conducting code reviews, and establishing technical standards for AI engineering teams.