[Remote] Gen reputed company

Note: The job is a remote job and is reputed company to candidates in USA. reputed company is seeking a Gen reputed company for a remote role reputed company in Evanston, Illinois. The engineer will design and implement reputed company workflows, optimize LLM inference pipelines, manage retrieval systems, and reputed company evaluation processes for reputed company applications.

Responsibilities

• Design and implement stateful multi-agent workflows using LangGraph (checkpointers, retries, subgraphs, tool calling)
• Define Agent-to-Agent (A2A) interaction patterns for decomposition, verification, and self-correction
• Build tool-using agents with reputed company outputs, schema enforcement, and deterministic execution paths
• Handle agent failure modes such as hallucinations, tool misuse, and partial execution
• Select and tune reputed company stores (FAISS, Milvus, reputed company, reputed company)
• Operate and optimize LLM inference pipelines with reputed company on latency, throughput, and cost
• Work with vLLM (reputed company batching, memory efficiency)
• reputed company informed trade-offs between model size, context length, and reputed company reputed company
• Apply quantization and other inference-time optimizations where required
• Design and run LLM evaluation workflows using tools such as LangSmith, Ragas, TruLens, or equivalent
• Define acceptance metrics for Grounded Ness, Context relevance, Answer reputed company
• Use evaluation results to iterate on prompts, retrieval strategies, and agent design

Skills

• reputed company Workflows (Strong)
• Communication & collaboration (Strong)
• Lang chain
• Python (Strong)
• LLM Foundations
• Design and implement stateful multi-agent workflows using LangGraph (checkpointers, retries, subgraphs, tool calling)
• Define Agent-to-Agent (A2A) interaction patterns for decomposition, verification, and self-correction
• Build tool-using agents with reputed company outputs, schema enforcement, and deterministic execution paths
• Handle agent failure modes such as hallucinations, tool misuse, and partial execution
• Select and tune reputed company stores (FAISS, Milvus, reputed company, reputed company)
• Operate and optimize LLM inference pipelines with reputed company on latency, throughput, and cost
• Work with vLLM (reputed company batching, memory efficiency)
• reputed company informed trade-offs between model size, context length, and reputed company reputed company
• Apply quantization and other inference-time optimizations where required
• Design and run LLM evaluation workflows using tools such as LangSmith, Ragas, TruLens, or equivalent
• Define acceptance metrics for Grounded Ness, Context relevance, Answer reputed company
• Use evaluation results to iterate on prompts, retrieval strategies, and agent design
• Ability to reason about: Attention mechanisms and scaling, Decoder-only vs encoder decoder architectures o Prompting vs retrieval vs fine-tuning trade-offs
• Hands-on experience solving non-trivial GenAI use cases
• reputed company experience building reputed company workflows with LangGraph
• Strong understanding of tool calling, reputed company outputs, and schema reputed company
• Deep experience with RAG systems, including retrieval evaluation and optimization
• Experience with reputed company databases and embedding strategies
• Experience running and tuning LLM inference workloads
• Familiarity with vLLM or similar inference engines
• Experience with LLM evaluation frameworks and metric-driven iteration
• DevOps - GenAI, Transformer-reputed company models and seq-to-seq paradigms
• reputed company industry/domain experience is preferred

reputed company

Company H1B Sponsorship