Senior LLM / Generative AI / Agentic Solutions Engineer
Confirmed on the employer's own hiring board on Sep 25, 2026. First seen by Alion on Jul 8, 2026.
Career Growth
Collaborative Team
Exciting Projects
Remote Work
Responsibilities
Build Agentic Systems: Design supervisor/executor patterns, memory strategies, and robust tool-calling failure handling.
LLM Adaptation & Deployment: Fine-tune open-source models and optimize inference for production-scale latency and cost.
Advanced RAG: Implement high-performance embedding, retrieval, and re-ranking pipelines for grounded outputs.
Structured Generation: Enforce schemas and guardrails to minimize hallucinations and ensure reliable system behavior.
Evaluation & Quality: Develop automated evaluation harnesses, regression tests, and versioning for prompts and models.
Production Engineering: Ship containerized APIs with full CI/CD, observability, and reliability monitoring (SLOs).
Cross-functional Delivery: Collaborate with product teams to integrate GenAI features and mentor junior engineers.
Requirements
Senior AI Expertise: 5+ years building production ML/AI systems, including 2+ years in lead roles with strong Python engineering (performance, testing, packaging).
LLM & Agentic AI: Hands-on experience with orchestration, tool-calling, and workflow integration, including LLM adaptation (PEFT/LoRA) and safety engineering.
Production RAG & Data: Proven track record of operating RAG pipelines, vector databases, and retrieval performance tuning in production.
MLOps & Cloud: Proficiency in containerized services (REST/gRPC), CI/CD, and monitoring within cloud environments (AWS/GCP/Azure).
Advanced Optimization: Experience in inference optimization (vLLM/quantization), event-driven orchestration, and automated evaluation (LLM-as-judge).